© 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. 159025
    Prev
    Next
    INDEX
    Explanations

    consolidation fees

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

    extract commands

    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
    et
    0.55
    ᱴ
    0.50
    ']->
    0.47
    HLA
    0.46
    ')):
    0.45
    گذاری
    0.45
    kT
    0.44
     enjoined
    0.44
    дио
    0.44
    MSFont
    0.43
    POSITIVE LOGITS
     Damages
    0.49
     Conflict
    0.46
     मनोहर
    0.45
     Elaine
    0.45
     conten
    0.44
     Highlight
    0.44
    hann
    0.44
     Edgar
    0.43
    屐
    0.43
     alter
    0.42
    Activations Density 0.000%

    No Known Activations