© 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. 95006
    Prev
    Next
    INDEX
    Explanations

    reserves concept, immunity boosters, sustainable gains, carrying case, actors' anger

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

    organization and numbers

    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
    ма
    0.47
    리
    0.46
    ра
    0.43
    ки
    0.43
    은
    0.43
    ба
    0.42
    пи
    0.42
    יל
    0.42
    ли
    0.42
    бо
    0.42
    POSITIVE LOGITS
     B
    0.35
     Drei
    0.33
     hedon
    0.32
     ه
    0.32
     antiguas
    0.31
     Centre
    0.31
     Eugène
    0.31
     Gruppe
    0.31
     Técn
    0.31
     ursprüng
    0.31
    Activations Density 0.027%

    No Known Activations