© 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. 116470
    Prev
    Next
    INDEX
    Explanations

    common phrases and follow-ups

    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
     absolutamente
    -1.23
     our
    -1.19
     ingress
    -0.97
    Mô
    -0.93
    Informa
    -0.93
     bona
    -0.91
    telefon
    -0.90
    Informations
    -0.90
     treff
    -0.90
    实的
    -0.89
    POSITIVE LOGITS
    nieuw
    1.15
     suoi
    1.02
     ситуации
    1.00
    ográficas
    1.00
     mostrarán
    0.98
    idespread
    0.97
    izaje
    0.97
     especially
    0.96
     filós
    0.96
    lossenen
    0.95
    Activations Density 0.026%

    No Known Activations