© 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. 101501
    Prev
    Next
    INDEX
    Explanations

    league, slow response, sized copies

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

    my responses will always be text

    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
     ব্যক্তি
    0.49
    AZ
    0.48
    num
    0.48
    NUM
    0.47
    MANY
    0.46
    %)
    0.46
    時間
    0.46
    車種
    0.45
    研究
    0.45
    更多
    0.44
    POSITIVE LOGITS
     falle
    0.61
     верну
    0.53
     воз
    0.50
    ВП
    0.47
     goes
    0.45
     requer
    0.45
     ofreci
    0.45
    ර්ශ
    0.45
     incandescent
    0.44
     intend
    0.43
    Activations Density 0.001%

    No Known Activations