© 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. 239312
    Prev
    Next
    INDEX
    Explanations

    NOT on this list

    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
    cation
    0.49
    bat
    0.47
    ア
    0.46
    F
    0.46
    name
    0.45
    IP
    0.45
    ה
    0.45
    a
    0.44
    фа
    0.44
    resa
    0.44
    POSITIVE LOGITS
     billowing
    0.48
     causative
    0.46
     Giorgio
    0.46
     Mahmoud
    0.46
    ۔
    0.45
     that
    0.44
     palazzo
    0.44
     causality
    0.44
     sediments
    0.43
     efek
    0.43
    Activations Density 0.004%

    No Known Activations