© 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. 49221
    Prev
    Next
    INDEX
    Explanations

    get file type

    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
    征
    -0.69
    <<<<<<<
    -0.69
     kérdés
    -0.64
    霹
    -0.64
    ígen
    -0.64
     manifestazione
    -0.64
     dimensione
    -0.63
    Recur
    -0.63
    是一位
    -0.63
    Comunic
    -0.63
    POSITIVE LOGITS
    Rachel
    0.79
     Desember
    0.77
     Joel
    0.73
     barley
    0.73
     Rachel
    0.73
    latex
    0.73
    wikipedia
    0.72
    corrhi
    0.72
    ᄋ
    0.71
    becca
    0.70
    Activations Density 0.039%

    No Known Activations