© 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. 30861
    Prev
    Next
    INDEX
    Explanations

    XML and code files

    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
    setStyle
    -0.73
    Overrides
    -0.73
    Ar
    -0.68
     One
    -0.67
     Turns
    -0.66
    ajuku
    -0.66
     Ли
    -0.65
    诉
    -0.65
    Paul
    -0.63
    stra
    -0.63
    POSITIVE LOGITS
    🕴
    0.76
    gratis
    0.74
     biomarker
    0.73
    iram
    0.72
    }~
    0.69
    yayım
    0.69
     abierto
    0.69
    rects
    0.68
    OTO
    0.67
    Facile
    0.67
    Activations Density 0.072%

    No Known Activations