© 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. 189268
    Prev
    Next
    INDEX
    Explanations

    naming and describing

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

    often mistaken

    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
    Representative
    0.50
     Farewell
    0.46
    daction
    0.46
     Laplacian
    0.45
    #'
    0.45
    deo
    0.44
    pian
    0.43
     Rational
    0.43
    Goodbye
    0.42
     값
    0.42
    POSITIVE LOGITS
     wichtige
    0.50
     perfekte
    0.46
     publi
    0.45
     moniker
    0.45
     صاح
    0.43
     beeindruck
    0.43
    ವೂ
    0.43
     inklusive
    0.42
     आरोप
    0.42
     genannt
    0.42
    Activations Density 0.000%

    No Known Activations