© 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. 22-GEMMASCOPE-RES-131K
    7. 39944
    Prev
    Next
    INDEX
    Explanations

    short story or stories

    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_22/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
     June
    -0.99
    G
    -0.97
    orElseThrow
    -0.97
     Cost
    -0.96
    B
    -0.95
     fiyatları
    -0.95
    έ
    -0.94
     Value
    -0.91
     robić
    -0.91
    U
    -0.91
    POSITIVE LOGITS
     rique
    1.47
     short
    1.21
     cristianismo
    1.20
     کوتاه
    1.16
    czenie
    1.16
    ämän
    1.14
     químico
    1.13
     cortos
    1.12
    хотво
    1.12
    حيح
    1.11
    Activations Density 0.044%

    No Known Activations