© 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. 251510
    Prev
    Next
    INDEX
    Explanations

    housing density

    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
    باً
    0.52
    ياً
    0.50
    يط
    0.44
    utsch
    0.44
    واي
    0.44
    vať
    0.44
    క
    0.43
     بِ
    0.43
    uie
    0.42
     Squares
    0.42
    POSITIVE LOGITS
    段时间
    0.53
    Businessman
    0.52
    businessman
    0.52
     maniak
    0.49
    periode
    0.47
    civil
    0.46
    Titan
    0.46
     bodhis
    0.46
     bande
    0.46
    damn
    0.46
    Activations Density 0.001%

    No Known Activations