© 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. 217705
    Prev
    Next
    INDEX
    Explanations

    data and instructions

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

    words after "is" or specific tokens

    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
    佅
    0.52
     inclination
    0.49
     infringing
    0.49
    ローン
    0.49
     requisitos
    0.47
    ЕС
    0.47
    빴
    0.47
    ා
    0.46
    增加了
    0.46
    பின்
    0.45
    POSITIVE LOGITS
     Forms
    0.48
    kul
    0.46
    s
    0.44
     Sebab
    0.43
     Put
    0.42
    Puzzle
    0.42
    kek
    0.41
    App
    0.41
     Context
    0.41
     Pues
    0.41
    Activations Density 0.000%

    No Known Activations