© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 217328
    Prev
    Next
    INDEX
    Explanations

    numbers with commas

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

    large numbers and quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .
    0.55
     resposta
    0.47
     respostas
    0.47
     vento
    0.45
     brasileira
    0.45
     allemand
    0.45
    ANA
    0.45
     być
    0.44
     penchant
    0.44
     froide
    0.44
    POSITIVE LOGITS
    ０
    0.68
    u
    0.67
    Hundreds
    0.65
    h
    0.64
    a
    0.63
    thousand
    0.60
    ה
    0.60
    <0x80>
    0.59
    ти
    0.58
    m
    0.57
    Activations Density 0.164%

    No Known Activations