© 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. 10-GEMMASCOPE-RES-131K
    7. 102221
    Prev
    Next
    INDEX
    Explanations

    penetration of substances or spaces

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

    The neuron detects the word "penetration" and its usage in relation to movement through physical barriers or into spaces.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    al
    -3.89
    The
    -3.44
    ak
    -3.11
    as
    -3.08
    {
    -3.05
    u
    -2.95
    he
    -2.84
    en
    -2.81
    I
    -2.72
    ad
    -2.61
    POSITIVE LOGITS
    潆
    3.58
    ୌ
    3.02
    ଃ
    2.98
    螣
    2.92
    ߹
    2.77
    檍
    2.75
    絝
    2.67
    疴
    2.64
    ixante
    2.59
    ⃢
    2.59
    Activations Density 0.005%

    No Known Activations