© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 136529
    Prev
    Next
    INDEX
    Explanations

    instructions or rules

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

    your, its, own

    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
     ゆっくり
    0.50
     カラ
    0.48
     化粧
    0.47
    ELS
    0.46
     剤
    0.46
     コーヒー
    0.46
     continueRoutine
    0.46
    ческих
    0.45
    ยังมี
    0.45
     опа
    0.44
    POSITIVE LOGITS
    toJSON
    0.47
     فائ
    0.47
     laaj
    0.44
    Founded
    0.43
    sizes
    0.43
    posX
    0.42
    Roaming
    0.42
     founded
    0.42
    blockSize
    0.42
    坊
    0.42
    Activations Density 0.000%

    No Known Activations