© 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. 190860
    Prev
    Next
    INDEX
    Explanations

    parenthetical phrases

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

    animal traits and actions

    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
    anders
    0.50
    calling
    0.44
     excepted
    0.43
     móc
    0.43
    坤
    0.43
     onPressed
    0.42
    conditioned
    0.42
     ade
    0.42
    suites
    0.42
    ブ
    0.42
    POSITIVE LOGITS
     philosophie
    0.57
     kemenangan
    0.56
     pensamento
    0.54
     romanzo
    0.54
     riforma
    0.54
     çöz
    0.53
     público
    0.53
     sfâr
    0.52
    ahaman
    0.52
     personalidade
    0.52
    Activations Density 0.003%

    No Known Activations