© 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. 12532
    Prev
    Next
    INDEX
    Explanations

    story, quests, places

    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
     juríd
    0.48
     immunore
    0.44
     イラスト
    0.43
     けれど
    0.43
     いたし
    0.43
    🧤
    0.42
    🍾
    0.42
     bioqu
    0.42
    ల్‌
    0.42
     arrondie
    0.42
    POSITIVE LOGITS
    setName
    0.44
     K
    0.43
    ibt
    0.40
    wish
    0.40
     NOM
    0.40
    oga
    0.39
     Asia
    0.38
    iger
    0.38
    chooser
    0.38
    渲染
    0.38
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.