© 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. 128695
    Prev
    Next
    INDEX
    Explanations

    a point of reference

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

    witty expressions and quotes

    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
     e
    0.54
     Haq
    0.47
    0.46
     evacu
    0.46
     Acoustics
    0.45
     influence
    0.43
     arom
    0.43
     Ease
    0.43
     conund
    0.41
     vigor
    0.41
    POSITIVE LOGITS
    ！”
    0.49
    ্ট
    0.48
    ్యాచ్
    0.47
    皂
    0.46
    monary
    0.45
    ной
    0.45
    рті
    0.45
    程式
    0.44
    rifft
    0.44
     жі
    0.43
    Activations Density 0.002%

    No Known Activations