© 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. 110494
    Prev
    Next
    INDEX
    Explanations

    latest updates

    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
    inerario
    -1.42
     superfí
    -1.30
    provides
    -1.25
    푉
    -1.25
     distintos
    -1.22
    UARIO
    -1.18
    をよく
    -1.18
     Institu
    -1.18
     ExecuteAsync
    -1.17
    colgante
    -1.17
    POSITIVE LOGITS
     addition
    2.17
     additions
    1.99
     developments
    1.89
     updates
    1.77
     information
    1.68
     from
    1.66
     update
    1.66
     iteration
    1.64
     on
    1.52
     incarnation
    1.52
    Activations Density 0.032%

    No Known Activations