© 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. 10-GEMMASCOPE-RES-131K
    7. 641
    Prev
    Next
    INDEX
    Explanations

    subject classification using "a"

    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_10/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
    From
    -1.91
    Now
    -1.88
    People
    -1.87
    What
    -1.86
     your
    -1.81
    Just
    -1.75
    When
    -1.74
    There
    -1.73
    Have
    -1.70
    Take
    -1.70
    POSITIVE LOGITS
     are
    2.59
    upto
    1.66
     themselves
    1.64
    effectively
    1.64
    themselves
    1.59
     adorned
    1.55
    larg
    1.55
     adelantado
    1.53
    jusqu
    1.52
    
    1.48
    Activations Density 0.059%

    No Known Activations