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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 119038
    Prev
    Next
    INDEX
    Explanations

    academic conference posters

    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
    čená
    -0.69
     House
    -0.66
     History
    -0.66
    LLocation
    -0.66
     Mass
    -0.66
    孀
    -0.65
     zurück
    -0.65
    的说道
    -0.65
    天王
    -0.65
     tools
    -0.64
    POSITIVE LOGITS
     poster
    3.34
    poster
    2.83
    Poster
    2.73
     posters
    2.73
     Poster
    2.70
     Posters
    2.23
     abstracts
    2.16
    Abstracts
    2.08
    Posters
    1.97
    posters
    1.95
    Activations Density 0.034%

    No Known Activations