© 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. 99878
    Prev
    Next
    INDEX
    Explanations

    evaluation, testing, development, beta

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

    business legal and strategic goals

    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
    Step
    0.50
    Box
    0.45
    ";
    0.44
    用
    0.42
    AN
    0.42
    emption
    0.42
    ूज
    0.42
     detonations
    0.42
     வழிபட்ட
    0.41
    ",
    0.41
    POSITIVE LOGITS
     Gestaltung
    0.50
     vielfält
    0.50
     საშ
    0.48
    addPreferred
    0.47
     LEC
    0.47
     réglement
    0.46
     README
    0.46
    锰
    0.46
     Unfall
    0.46
     Reise
    0.45
    Activations Density 0.000%

    No Known Activations