© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1194
    Prev
    Next
    INDEX
    Explanations

    tracking specific titles

    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
     dictadura
    -0.74
     zwykle
    -0.71
     ruhig
    -0.71
    lant
    -0.71
     हर
    -0.70
    柔軟
    -0.70
    是小
    -0.69
     Paral
    -0.69
    jol
    -0.69
    xico
    -0.68
    POSITIVE LOGITS
    Jimin
    0.76
    رة
    0.75
    Titan
    0.75
     televised
    0.75
     Jamal
    0.74
    Cowboy
    0.73
    Saturn
    0.73
    toggleClass
    0.72
    改
    0.71
     Olu
    0.70
    Activations Density 0.006%

    No Known Activations