© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 87149
    Prev
    Next
    INDEX
    Explanations

    Hawaii, Institute, Fire, XML

    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
     tege
    -0.78
     intim
    -0.73
     preguntó
    -0.68
    matur
    -0.68
    aneta
    -0.68
    cosal
    -0.68
     positivos
    -0.67
     statewide
    -0.67
    atifs
    -0.67
    azzi
    -0.67
    POSITIVE LOGITS
     Honolulu
    0.87
     Koko
    0.84
     Pearl
    0.82
    ੜ
    0.76
    ully
    0.76
    Pearl
    0.73
    Honolulu
    0.73
     Capa
    0.72
    去的
    0.72
    ented
    0.71
    Activations Density 0.022%

    No Known Activations