© 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. 22-GEMMASCOPE-RES-131K
    7. 12308
    Prev
    Next
    INDEX
    Explanations

    business services and markets

    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
     because
    -1.30
     something
    -1.30
     all
    -1.16
     When
    -1.14
     my
    -1.13
     katholischen
    -1.12
     our
    -1.11
     vielleicht
    -1.09
     things
    -1.08
     people
    -1.07
    POSITIVE LOGITS
     will
    1.38
     THEATRE
    1.38
    Commenting
    1.31
     philippe
    1.27
     VOOR
    1.27
     ofrecemos
    1.19
    кож
    1.17
    hindi
    1.16
     pensez
    1.13
     onsdag
    1.13
    Activations Density 0.094%

    No Known Activations