© 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. 161076
    Prev
    Next
    INDEX
    Explanations

    protest outside, movement, you wish

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

    ordering, control, relationships

    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
    诮
    0.46
     prü
    0.46
    修理
    0.45
    硫酸
    0.45
    里斯
    0.45
    税
    0.45
     են
    0.44
    履行
    0.44
     locu
    0.44
    修建
    0.44
    POSITIVE LOGITS
    ielt
    0.49
     Accepting
    0.47
     Glasgow
    0.47
    elho
    0.44
    ateau
    0.44
     ALEXANDER
    0.43
     változat
    0.42
     Gle
    0.42
     απε
    0.42
    讚
    0.41
    Activations Density 0.000%

    No Known Activations