© 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. 57185
    Prev
    Next
    INDEX
    Explanations

    organization information

    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
    icoli
    -0.84
     оте
    -0.84
    ceği
    -0.76
     vært
    -0.75
     Cancelar
    -0.75
    ヶ
    -0.75
     Lietuvos
    -0.74
     intolerance
    -0.74
    Olymp
    -0.73
    誥
    -0.73
    POSITIVE LOGITS
    JvmStatic
    0.82
    nija
    0.82
    렙
    0.81
     Darío
    0.79
    letzt
    0.78
    身長
    0.77
     Cloak
    0.77
     Ety
    0.76
    EventData
    0.76
     izan
    0.76
    Activations Density 0.024%

    No Known Activations