© 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. 717
    Prev
    Next
    INDEX
    Explanations

    introduction, test, stream

    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
    ܆
    -1.98
     mojej
    -1.98
     miniaturka
    -1.96
    岽
    -1.92
    𓆏
    -1.88
     électron
    -1.87
     pistolet
    -1.84
     incrí
    -1.81
     phénom
    -1.80
     indiví
    -1.80
    POSITIVE LOGITS
     it
    2.61
    </h2>
    2.25
     может
    2.08
     and
    2.05
     everything
    2.00
     how
    1.97
     will
    1.96
     an
    1.82
     what
    1.82
     we
    1.81
    Activations Density 0.101%

    No Known Activations