© 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. 2956
    Prev
    Next
    INDEX
    Explanations

    12VDC or AC power

    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
    托管
    -0.81
     tratamento
    -0.77
    DBNull
    -0.73
    ikation
    -0.72
    neuron
    -0.71
    ્ર
    -0.71
     risers
    -0.69
    servers
    -0.69
    满满
    -0.68
    chließend
    -0.68
    POSITIVE LOGITS
     cigarette
    1.89
     Cigarette
    1.55
    cigarette
    1.47
     DC
    1.45
     lighter
    1.23
     cig
    1.22
     dc
    1.16
    DC
    1.11
     car
    1.08
     cigar
    1.08
    Activations Density 0.022%

    No Known Activations