© 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. 90439
    Prev
    Next
    INDEX
    Explanations

    regular transfers, standard module, asking questions

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

    services, options, or loss

    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
    ╳
    0.51
    useful
    0.49
     hint
    0.49
     lyophil
    0.49
     gases
    0.47
     concomit
    0.47
     utile
    0.47
     (+)
    0.46
    薨
    0.46
     concussion
    0.46
    POSITIVE LOGITS
     Landkreis
    0.52
    誢
    0.50
    デックス
    0.48
    vær
    0.46
     Bä
    0.45
    ونها
    0.45
    城県
    0.44
    IDADES
    0.44
    ляются
    0.44
    itada
    0.44
    Activations Density 0.000%

    No Known Activations