© 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. 211351
    Prev
    Next
    INDEX
    Explanations

    syndicated temperatures yield products

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

    programming concepts and class casting

    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
     dare
    0.48
     daring
    0.46
    '
    0.46
     jail
    0.45
     sams
    0.44
    ខ
    0.42
    Congress
    0.41
    加え
    0.41
    िव
    0.40
     gelang
    0.40
    POSITIVE LOGITS
     Preset
    0.51
    မှုကို
    0.50
     Cornerstone
    0.49
    镟
    0.47
    阐
    0.46
    CompliancePolicy
    0.45
     સંપૂર્ણ
    0.45
    ឫ
    0.45
    orbid
    0.45
    vrdr
    0.45
    Activations Density 0.001%

    No Known Activations