© 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. 203591
    Prev
    Next
    INDEX
    Explanations

    header, search, would, example, if

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

    bits and light switches

    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
    ®
    0.52
    NA
    0.50
     Acura
    0.49
     Yokohama
    0.48
    I
    0.47
     Bridgeport
    0.46
    ]={
    0.46
    瞼
    0.45
    
    0.45
     Pontiac
    0.45
    POSITIVE LOGITS
     índices
    0.55
     기준
    0.49
    ર્ટ
    0.49
     기준으로
    0.48
     정의역
    0.46
     ब्रे
    0.45
    <unused2162>
    0.45
     variétés
    0.44
     tür
    0.43
     شورای
    0.43
    Activations Density 0.000%

    No Known Activations