© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129893
    Prev
    Next
    INDEX
    Explanations

    conjunctions or list separators

    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
    ⦊
    -2.50
    虓
    -2.14
    sistent
    -2.05
     cię
    -1.92
     réve
    -1.88
    ſtra
    -1.82
    ～～～
    -1.77
     głowy
    -1.76
    関節
    -1.75
     waar
    -1.74
    POSITIVE LOGITS
    '
    2.55
     between
    2.13
     was
    2.13
     are
    2.05
    </sub>
    2.05
    S
    2.05
    </h3>
    2.02
    archiwizowane
    1.98
    }
    1.95
     either
    1.86
    Activations Density 0.002%

    No Known Activations