© 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. 22-GEMMASCOPE-RES-131K
    7. 74878
    Prev
    Next
    INDEX
    Explanations

    chemical elements and indices

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

    mathematical notation, particularly equal signs in equations or variable definitions.

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

    The neuron is primarily detecting numeric tokens (numbers, including integers and decimals).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     Excellent
    -1.20
     excellent
    -1.09
     by
    -1.07
     when
    -1.02
     overtly
    -1.02
    Ⅽ
    -1.02
     JUST
    -1.01
     There
    -1.00
     procedures
    -0.99
     issues
    -0.98
    POSITIVE LOGITS
    都没
    1.13
    both
    1.08
     Dinas
    1.07
     deaktiviert
    1.04
     notamment
    1.04
     étend
    1.02
    entraî
    1.00
    rentes
    1.00
     scrittura
    1.00
     ausein
    0.99
    Activations Density 0.011%

    No Known Activations