© 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. 34-GEMMASCOPE-RES-131K
    7. 118777
    Prev
    Next
    INDEX
    Explanations

    page or page format

    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_34/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
     repetitions
    -0.80
     riffs
    -0.80
    هاء
    -0.75
     fielder
    -0.73
    бля
    -0.72
     плот
    -0.72
     couplings
    -0.71
     Newbury
    -0.71
     electoral
    -0.70
    hapsody
    -0.70
    POSITIVE LOGITS
     page
    0.99
     pages
    0.95
     mono
    0.82
    idez
    0.82
    Produce
    0.77
    ENNE
    0.77
     serre
    0.76
     페이지
    0.75
    Hig
    0.75
    pagina
    0.74
    Activations Density 0.041%

    No Known Activations