© 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. 117305
    Prev
    Next
    INDEX
    Explanations

    XML Schema types

    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
    Ⓣ
    -0.77
    ществует
    -0.76
     kaca
    -0.72
     territ
    -0.71
     Demonstr
    -0.71
    पाद
    -0.71
     Чем
    -0.69
     Verarbeitung
    -0.67
    qry
    -0.67
    resa
    -0.67
    POSITIVE LOGITS
    anese
    0.81
     badass
    0.78
    chtenstein
    0.78
     Chill
    0.78
    conian
    0.77
     futbolista
    0.76
    ématiques
    0.75
    cycline
    0.73
     Urlaub
    0.72
    रो
    0.72
    Activations Density 0.001%

    No Known Activations