© 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. 231668
    Prev
    Next
    INDEX
    Explanations

    lenticular

    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
     occupy
    0.48
    ün
    0.46
     برابر
    0.46
    ángulos
    0.46
    𝐕
    0.45
    𝐎
    0.45
     खुलकर
    0.45
    வ
    0.44
    йн
    0.44
    ük
    0.44
    POSITIVE LOGITS
    Thailand
    0.52
     neurolog
    0.44
    Travis
    0.44
     Thailand
    0.43
    Nigeria
    0.43
    沖縄
    0.43
     moz
    0.42
    Dirt
    0.42
     androgen
    0.42
    才會
    0.42
    Activations Density 0.000%

    No Known Activations