© 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. 19733
    Prev
    Next
    INDEX
    Explanations

    author-date system

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

    natural, nationality, nature

    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
    addSprite
    0.51
    願い
    0.49
    くだ
    0.48
    🔍
    0.48
    angulo
    0.47
     காணலாம்
    0.47
    図
    0.46
    皤
    0.46
    Geometry
    0.46
    痘
    0.46
    POSITIVE LOGITS
     natu
    0.53
     kř
    0.50
     sosial
    0.50
     managing
    0.49
    kring
    0.48
     obligaciones
    0.48
     socialization
    0.48
     comidas
    0.48
     psychologists
    0.48
    natural
    0.48
    Activations Density 0.000%

    No Known Activations