© 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. 108820
    Prev
    Next
    INDEX
    Explanations

    css url and links

    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
     Munk
    -0.82
    Ĺ
    -0.78
    orghini
    -0.76
    дует
    -0.73
    édie
    -0.71
    дивиду
    -0.70
    verly
    -0.69
    raquo
    -0.69
    lgari
    -0.69
     czuj
    -0.68
    POSITIVE LOGITS
    יצוני
    0.72
    ⋯
    0.68
    istiques
    0.65
     dars
    0.63
    ガス
    0.63
     TSC
    0.63
     Samar
    0.62
     freel
    0.62
     கி
    0.62
     главный
    0.60
    Activations Density 0.039%

    No Known Activations