© 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. 18759
    Prev
    Next
    INDEX
    Explanations

    © copyright and proper nouns

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

    propose, call, host, hoard

    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
     Österreich
    0.52
     možnost
    0.49
    rossover
    0.49
    غا
    0.48
     Ländern
    0.47
     együtt
    0.47
    TPP
    0.46
    ”:
    0.46
    敝
    0.46
     Kroger
    0.45
    POSITIVE LOGITS
    Ace
    0.46
    Url
    0.46
     ceil
    0.45
    Belt
    0.45
     toro
    0.45
     setelah
    0.45
    Drink
    0.44
     Cev
    0.44
    lll
    0.44
    Cel
    0.44
    Activations Density 0.000%

    No Known Activations