© 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. 45289
    Prev
    Next
    INDEX
    Explanations

    family in

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

    avoid, unlike, beyond

    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
    endous
    0.52
    ussels
    0.47
    imento
    0.47
    鳥
    0.46
    バン
    0.46
     outta
    0.46
    ());
    0.46
    Decedent
    0.46
    Erro
    0.45
    ConstPtr
    0.44
    POSITIVE LOGITS
     व्यायाम
    0.47
    ерез
    0.47
    に従
    0.46
     Casino
    0.45
    체가
    0.43
     Python
    0.43
     թ
    0.43
     อย่าง
    0.43
     bienvenue
    0.42
    부분
    0.42
    Activations Density 0.000%

    No Known Activations