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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 80811
    Prev
    Next
    INDEX
    Explanations

    conjunctions of contrast

    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
    洇
    -2.58
    re
    -2.58
    <td>
    -2.44
    )$
    -2.17
    镦
    -2.16
    躂
    -2.14
    },
    -2.11
    ED
    -2.11
    llten
    -2.11
    虽然
    -2.08
    POSITIVE LOGITS
     Recuperado
    2.19
    到底是
    2.08
    atiana
    2.03
     häufigsten
    1.97
    $
    1.95
    ﹝
    1.88
    jine
    1.84
    5
    1.83
    (
    1.83
    maglia
    1.83
    Activations Density 0.000%

    No Known Activations