© 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. 162858
    Prev
    Next
    INDEX
    Explanations

    empathy or allies and showing selected

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

    domain names or prices

    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
    外出
    0.48
    రువు
    0.46
     updateTotal
    0.44
    დე
    0.44
    bation
    0.43
     prestations
    0.42
     trembling
    0.42
     석
    0.42
     totals
    0.41
     opérations
    0.41
    POSITIVE LOGITS
     NYC
    0.52
     hakkında
    0.48
     page
    0.48
     Specifies
    0.47
     kommt
    0.44
     jugó
    0.44
     Pico
    0.44
     juega
    0.44
     ejemplo
    0.43
     webpage
    0.43
    Activations Density 0.001%

    No Known Activations