© 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. 183592
    Prev
    Next
    INDEX
    Explanations

    proper nouns and places

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

    some limitations

    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
    łą
    0.54
    hydrate
    0.53
     ጣ
    0.52
    hydration
    0.52
    loat
    0.52
    л
    0.52
     affront
    0.51
    ethyl
    0.50
    iring
    0.50
    '-
    0.49
    POSITIVE LOGITS
     Treasurer
    0.47
     Schwartz
    0.47
    が変わ
    0.47
     Kluwer
    0.47
     Chancery
    0.46
     Augsburg
    0.46
     Grower
    0.46
     Burger
    0.46
     CHI
    0.46
     Leap
    0.46
    Activations Density 0.001%

    No Known Activations