© 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. 73405
    Prev
    Next
    INDEX
    Explanations

    mention this, complete your, below button, simulator assessments

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

    indestructible, slow blinking, misuse

    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
    xh
    0.56
    Cookie
    0.50
    w
    0.49
    strftime
    0.47
    ジ
    0.46
    igr
    0.46
    ach
    0.45
    W
    0.45
    خب
    0.44
    ｾ
    0.44
    POSITIVE LOGITS
     değeri
    0.58
     sanctuary
    0.54
     иной
    0.52
     имеются
    0.52
     основной
    0.52
     podstaw
    0.52
     episcopal
    0.49
     gymnasium
    0.48
     cavité
    0.47
     tủ
    0.47
    Activations Density 0.001%

    No Known Activations