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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57297
    Prev
    Next
    INDEX
    Explanations

    numbers and scientific contexts

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

    indentation at the beginning of paragraphs or code blocks.

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

    The neuron strongly activates on runs of space‐only tokens—i.e. chunks of indentation or long blank spacing.

    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
     without
    -1.04
     only
    -0.92
     since
    -0.87
     because
    -0.87
     Since
    -0.86
    捷
    -0.85
     when
    -0.84
    bottomRight
    -0.84
     Without
    -0.84
     Though
    -0.84
    POSITIVE LOGITS
     renovación
    0.88
     errichtet
    0.86
     ($.
    0.84
    汽車
    0.84
     einschließlich
    0.82
    さっき
    0.82
     mesmerizing
    0.82
     beantragt
    0.81
     LEARN
    0.81
    颠
    0.81
    Activations Density 0.000%

    No Known Activations