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. 12106
    Prev
    Next
    INDEX
    Explanations

    numbers and code syntax

    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
     agir
    -1.11
     ferocious
    -1.00
     amazing
    -1.00
     pagos
    -1.00
    ϋ
    -0.99
    ων
    -0.98
     クッション
    -0.98
     oraș
    -0.98
     joyous
    -0.97
     durch
    -0.97
    POSITIVE LOGITS
     for
    1.18
     during
    1.07
    :
    1.06
     regarding
    1.04
     as
    1.01
     only
    1.00
    ressee
    0.99
     other
    0.99
     itself
    0.96
     at
    0.92
    Activations Density 0.161%

    No Known Activations