© 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. 148903
    Prev
    Next
    INDEX
    Explanations

    casino, factor, Friday, ensuring

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

    dosages, analyses, historical data

    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
    喜
    0.51
    道
    0.49
    厚
    0.48
    PLE
    0.46
    偕
    0.46
    晟
    0.43
    దల
    0.43
    اون
    0.43
    友
    0.42
    轩
    0.42
    POSITIVE LOGITS
     operates
    0.58
     gives
    0.54
     airline
    0.53
     doesnt
    0.51
     permeates
    0.51
    ConstPtr
    0.49
     один
    0.49
     adheres
    0.48
     থাকিলেও
    0.48
     femminile
    0.47
    Activations Density 0.000%

    No Known Activations