© 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. 18116
    Prev
    Next
    INDEX
    Explanations

    creating implementation, works made, transformation functions, teaching classes

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

    definitions and descriptions

    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
    ka
    0.43
     sounds
    0.41
    x
    0.41
    String
    0.40
     ;
    0.40
    ma
    0.39
    anyo
    0.39
    p
    0.39
     his
    0.39
     ,
    0.38
    POSITIVE LOGITS
    гийн
    0.44
    ји
    0.43
    েন্দু
    0.43
    껄
    0.43
     neutralizing
    0.42
    DELAY
    0.41
    '،
    0.41
     cliche
    0.41
     meist
    0.41
    روی
    0.41
    Activations Density 0.000%

    No Known Activations