© 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. 92996
    Prev
    Next
    INDEX
    Explanations

    equivalency factor or new data

    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
     textStatus
    -0.74
     groves
    -0.73
     amenazas
    -0.72
     понятно
    -0.70
     Comics
    -0.70
     pério
    -0.70
    对面
    -0.69
     hài
    -0.68
     explain
    -0.68
     Gewerks
    -0.68
    POSITIVE LOGITS
     conversion
    2.03
    Conversion
    1.73
    conversion
    1.65
     Conversion
    1.57
     factor
    1.55
     factors
    1.52
     conversions
    1.44
    factor
    1.41
    factors
    1.25
    Factor
    1.22
    Activations Density 0.030%

    No Known Activations