© 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. 217423
    Prev
    Next
    INDEX
    Explanations

    indemnify held outstanding

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

    stars, requires, possibilities

    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
    ANAL
    0.48
    拔
    0.47
    끄
    0.46
     operar
    0.45
     donné
    0.44
     apparten
    0.44
    なく
    0.43
     pavatt
    0.43
    UNDER
    0.43
     fulfils
    0.43
    POSITIVE LOGITS
    綺
    0.52
     添加
    0.48
    screen
    0.46
    是因為
    0.46
    iston
    0.45
    ாடி
    0.44
    之所以
    0.44
    acency
    0.44
     Jing
    0.44
    情緒
    0.44
    Activations Density 0.000%

    No Known Activations