Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 11580
    Prev
    Next
    INDEX
    Explanations

    dates, codes, or numbers after a name

    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
    :~
    -0.98
     ataupun
    -0.92
    ménage
    -0.90
     fuoco
    -0.87
     uhd
    -0.85
     الان
    -0.84
     berbeda
    -0.84
    sssss
    -0.84
     wacht
    -0.81
    ⇐
    -0.81
    POSITIVE LOGITS
    ulante
    0.99
     Solskjaer
    0.93
     INFORMACIÓN
    0.93
     tournée
    0.92
    之时
    0.92
     simplesmente
    0.92
     suspendu
    0.90
     [''],
    0.90
     needlessly
    0.88
    Timings
    0.86
    Activations Density 0.009%

    No Known Activations