© 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. 251303
    Prev
    Next
    INDEX
    Explanations

    outcomes, damage, data, sector

    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
    name
    0.56
     I
    0.50
    toString
    0.49
    discovered
    0.47
    名前
    0.47
    ণ
    0.44
    types
    0.44
    nombre
    0.43
    ipine
    0.43
    ﺑ
    0.43
    POSITIVE LOGITS
     swat
    0.50
    蕖
    0.48
    绡
    0.48
    ø
    0.46
     konus
    0.44
     oyunc
    0.44
     üzerinde
    0.44
    खाव
    0.44
    ার্জি
    0.44
    াম
    0.43
    Activations Density 0.000%

    No Known Activations