© 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. 57719
    Prev
    Next
    INDEX
    Explanations

    information structures

    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
    cati
    -0.78
    phoric
    -0.74
     verke
    -0.73
     worded
    -0.72
    thos
    -0.71
     GLA
    -0.69
    Heart
    -0.67
     mieszkań
    -0.66
     Saal
    -0.66
    ctic
    -0.65
    POSITIVE LOGITS
     markedly
    0.70
    كام
    0.69
    ाषा
    0.66
    Destroyed
    0.65
    弱点
    0.63
    跆
    0.63
    推理
    0.62
    marketing
    0.62
    ဲ
    0.62
     Albright
    0.61
    Activations Density 0.060%

    No Known Activations