© 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. 40-GEMMASCOPE-2-RES-16K
    7. 9685
    Prev
    Next
    INDEX
    Explanations

    pictures of

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

    Your Request

    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_40_width_16k_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
    да
    0.59
     barcelona
    0.55
     anthropology
    0.54
     oauth
    0.54
     jihad
    0.53
    <unused1024>
    0.53
     पेंगे
    0.53
     marina
    0.51
     archaeology
    0.51
    ма
    0.50
    POSITIVE LOGITS
     Himself
    0.73
     Zweiten
    0.71
     Re
    0.69
     Red
    0.69
     Model
    0.68
     Series
    0.68
     Ş
    0.68
     H
    0.67
     Gobierno
    0.67
     Prosecutor
    0.67
    Activations Density 4.826%

    No Known Activations