© 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. 513
    Prev
    Next
    INDEX
    Explanations

    Interstate highways

    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
    </strong>
    -1.90
    </h2>
    -1.85
    <i>
    -1.71
    当下
    -1.65
    </b>
    -1.61
    .
    -1.55
    藹
    -1.55
     suggest
    -1.49
    <em>
    -1.47
    नो
    -1.46
    POSITIVE LOGITS
     continúas
    1.86
    ⤞
    1.84
    镚
    1.77
     pinta
    1.76
     solicita
    1.76
     dahil
    1.72
     puedo
    1.71
     incluso
    1.71
     dedica
    1.70
     comunica
    1.69
    Activations Density 0.013%

    No Known Activations