© 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. 53348
    Prev
    Next
    INDEX
    Explanations

    the federation

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

    defining systems and rules

    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
     strikingly
    0.47
    ༦
    0.46
     encountered
    0.45
     brightly
    0.45
    ༧
    0.45
    酈
    0.45
    ęp
    0.45
    קס
    0.45
     tylko
    0.45
     Kalyan
    0.45
    POSITIVE LOGITS
    callable
    0.46
    detector
    0.46
     Automatic
    0.44
    ্‌
    0.43
    mutable
    0.42
    minister
    0.41
    rtype
    0.41
    closures
    0.41
    baseUrl
    0.41
    ResponseType
    0.41
    Activations Density 0.000%

    No Known Activations