© 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. 86325
    Prev
    Next
    INDEX
    Explanations

    how to have

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

    technical terms followed by specifics

    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
     जुटे
    0.50
    lice
    0.47
    iae
    0.45
     రచ
    0.44
     ملی
    0.42
    imbus
    0.42
     сезо
    0.42
    [
    0.42
    荲
    0.42
     ход
    0.42
    POSITIVE LOGITS
     groceries
    0.46
     dren
    0.46
     grocery
    0.45
     voicemail
    0.45
     pauper
    0.45
     customer
    0.45
     shopper
    0.45
     supermarket
    0.44
     pobreza
    0.44
     scoreboard
    0.44
    Activations Density 0.002%

    No Known Activations