© 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. 11295
    Prev
    Next
    INDEX
    Explanations

    functions, projects, side, airport, elements, continents, variables, design, seamlessly, complex, advance, colonies

    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
     or
    -1.11
    например
    -1.07
     Maybe
    -1.05
     suivante
    -1.01
    properties
    -0.98
    property
    -0.98
    setUser
    -0.98
    あります
    -0.96
    ちゃんが
    -0.96
    obtenir
    -0.93
    POSITIVE LOGITS
     these
    1.36
     however
    1.26
     данного
    1.20
     данной
    1.16
     but
    1.13
     thus
    1.11
     queste
    1.10
    these
    1.07
     olduğu
    1.06
    このように
    1.06
    Activations Density 0.045%

    No Known Activations