© 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. 238307
    Prev
    Next
    INDEX
    Explanations

    submitted for assets score

    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
     Brewing
    0.48
     Drawings
    0.48
     colle
    0.47
     内
    0.46
     maturing
    0.42
    stimulated
    0.41
     servicing
    0.41
     Timing
    0.41
     Growth
    0.41
     Operations
    0.41
    POSITIVE LOGITS
     maniac
    0.49
     situações
    0.48
    sbParams
    0.47
     настолько
    0.47
    Насе
    0.46
     seconds
    0.46
    උ
    0.45
     uninhab
    0.45
    $=
    0.45
     unconsciously
    0.44
    Activations Density 0.001%

    No Known Activations