© 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. 64920
    Prev
    Next
    INDEX
    Explanations

    Nashville based

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

    strategies and advice

    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
     ignited
    0.54
     ganado
    0.54
    }^{*}=\
    0.52
     eines
    0.50
    ጼ
    0.50
     peach
    0.49
     cobert
    0.48
     phospho
    0.48
     sequelize
    0.47
     seines
    0.47
    POSITIVE LOGITS
    shap
    0.50
    2
    0.48
    odium
    0.47
    DON
    0.46
    埛
    0.43
    Don
    0.43
    Nya
    0.43
    kola
    0.42
    DC
    0.42
    7
    0.42
    Activations Density 0.000%

    No Known Activations