© 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. 197935
    Prev
    Next
    INDEX
    Explanations

    clean and ready

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

    describing visual appearance and qualities

    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
    mercial
    0.43
    mongoUrl
    0.41
     svojih
    0.39
     monographs
    0.39
     recurring
    0.39
    recurring
    0.39
    ﾟ
    0.39
    player
    0.38
    goto
    0.38
    [,,"
    0.38
    POSITIVE LOGITS
     Enth
    0.50
     Wound
    0.50
     Difficult
    0.46
     Floral
    0.46
     Escherichia
    0.46
     Adhesive
    0.46
     Mitochondrial
    0.46
     Pharmac
    0.46
     Nut
    0.46
     Burn
    0.45
    Activations Density 0.001%

    No Known Activations