© 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. 12345
    Prev
    Next
    INDEX
    Explanations

    types and categories

    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
     célè
    -1.78
     siè
    -1.74
     plafon
    -1.64
     poë
    -1.63
     rigide
    -1.59
     multicolore
    -1.57
     indescri
    -1.53
     maniere
    -1.49
     différents
    -1.46
     meub
    -1.46
    POSITIVE LOGITS
     which
    1.95
     it
    1.66
     more
    1.64
     their
    1.56
     just
    1.52
     really
    1.52
     first
    1.51
     before
    1.49
     out
    1.48
     only
    1.48
    Activations Density 0.041%

    No Known Activations