© 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. 92995
    Prev
    Next
    INDEX
    Explanations

    factor / factors

    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
     svg
    -0.87
    ㄦ
    -0.86
    toCharArray
    -0.84
    OrEqual
    -0.79
    oded
    -0.78
    opencv
    -0.77
     Infirmary
    -0.76
    もちゃ
    -0.76
     Valerie
    -0.75
    Svg
    -0.74
    POSITIVE LOGITS
     factor
    2.64
     factors
    2.58
    factor
    2.23
    factors
    1.90
    Factor
    1.90
     Factor
    1.88
     Factors
    1.88
    因子
    1.74
    FACTOR
    1.70
     facteur
    1.67
    Activations Density 0.028%

    No Known Activations