© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 103736
    Prev
    Next
    INDEX
    Explanations

    MRI vs CT

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron activates for web page and document layout formatting elements like line breaks, spacing, and punctuation.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron fires on the key words used in imperative “how-to” or “tips” style headings (e.g. Keep, your, to, date) in tutorial/blog post titles.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     przecież
    -0.81
     poorest
    -0.79
    <0xB7>
    -0.75
    nologie
    -0.75
     распро
    -0.75
    Acrylic
    -0.72
    Operand
    -0.72
    borderWidth
    -0.71
     poorer
    -0.71
     visitas
    -0.70
    POSITIVE LOGITS
     SAG
    1.35
     headshot
    1.30
    SAG
    1.23
     submissions
    1.19
     casting
    1.16
     Casting
    1.15
     Actors
    1.14
    Casting
    1.12
     submission
    1.07
    booked
    1.07
    Activations Density 0.020%

    No Known Activations