© 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. 576
    Prev
    Next
    INDEX
    Explanations

    code blocks and literals

    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
     raiſ
    -2.03
    鹩
    -1.95
     remé
    -1.88
     camiset
    -1.86
    籙
    -1.83
    ₶
    -1.82
    涠
    -1.76
    艄
    -1.76
    
    -1.70
     excès
    -1.67
    POSITIVE LOGITS
    ).
    2.36
    It
    2.30
    }
    2.11
    :
    2.03
     and
    2.00
    They
    1.95
    =
    1.93
    There
    1.86
    _
    1.84
    >
    1.81
    Activations Density 0.110%

    No Known Activations