© 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. 11361
    Prev
    Next
    INDEX
    Explanations

    code syntax and punctuation

    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
     might
    -1.07
     to
    -1.00
     consists
    -0.99
     those
    -0.96
     could
    -0.92
     may
    -0.90
     some
    -0.90
     mostly
    -0.90
     usually
    -0.88
     until
    -0.86
    POSITIVE LOGITS
     evenement
    0.96
     incompar
    0.94
     definitivamente
    0.93
    thaf
    0.91
    orso
    0.88
    bản
    0.88
     aspar
    0.87
    lany
    0.85
    ATTLE
    0.84
    兴奋
    0.84
    Activations Density 0.001%

    No Known Activations