© 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. 12278
    Prev
    Next
    INDEX
    Explanations

    comparisons and conditions

    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
     kompeti
    -1.21
     chemise
    -1.20
     josé
    -1.19
    Geograf
    -1.16
     francisco
    -1.16
     itulah
    -1.14
     Etat
    -1.13
    тори
    -1.13
     protokol
    -1.13
    рочка
    -1.13
    POSITIVE LOGITS
     something
    1.13
     it
    1.13
     sometimes
    1.02
     anything
    1.02
     things
    0.99
     niebla
    0.96
     gastar
    0.96
     grasa
    0.95
    . 
    0.95
     není
    0.94
    Activations Density 0.068%

    No Known Activations