© 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. 88015
    Prev
    Next
    INDEX
    Explanations

    dates and months

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

    an abbreviation or initial

    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
     trải
    0.44
    jean
    0.44
     Suffering
    0.43
    𝑁
    0.43
    Having
    0.43
    SEE
    0.43
    $.\
    0.42
    噢
    0.42
    liy
    0.40
    ni
    0.39
    POSITIVE LOGITS
    ا
    0.54
    etés
    0.50
    ه
    0.50
     aspirated
    0.48
     florals
    0.48
     organs
    0.48
     cephal
    0.47
     squirrels
    0.46
     Dezember
    0.46
     anthropology
    0.46
    Activations Density 0.000%

    No Known Activations