© 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. 11308
    Prev
    Next
    INDEX
    Explanations

    function calls and arguments

    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
     voelen
    -1.04
    など
    -1.04
    НО
    -1.00
    子が
    -0.99
     jūs
    -0.98
     about
    -0.96
    islam
    -0.96
     salieron
    -0.94
     habrían
    -0.93
     Wiktionnaire
    -0.92
    POSITIVE LOGITS
     demselben
    1.27
     générer
    1.21
     montrer
    1.18
    で使
    1.18
     it
    1.16
     chercher
    1.09
     appeler
    1.09
     manquer
    1.09
     communiquer
    1.08
     procéder
    1.07
    Activations Density 0.004%

    No Known Activations