© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 2826
    Prev
    Next
    INDEX
    Explanations

    brave rescue, lone policeman, checking ID

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     African
    -1.12
     african
    -1.04
     Hispanics
    -1.03
     Ife
    -1.00
     asian
    -1.00
     Asians
    -0.99
    Източници
    -0.99
    St
    -0.97
     Asian
    -0.96
     milyon
    -0.96
    POSITIVE LOGITS
     internally
    1.10
     horribly
    1.05
    ūros
    1.02
     weddings
    1.01
     pomegranate
    0.97
    haled
    0.96
     descre
    0.96
     mężczyzn
    0.95
     rudimentary
    0.95
    NGO
    0.94
    Activations Density 0.075%

    No Known Activations