© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 78580
    Prev
    Next
    INDEX
    Explanations

    code elements and structure delimiters

    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_34/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
    <?>
    -1.12
    [:]
    -0.74
    dles
    -0.72
     pprint
    -0.72
    ested
    -0.71
     kuma
    -0.69
    дро
    -0.69
    worths
    -0.63
     javafx
    -0.63
    ख्या
    -0.63
    POSITIVE LOGITS
     "",
    2.36
     '',
    2.17
    ("",
    2.13
    <?,
    1.93
     _,
    1.92
    "",
    1.91
    ('',
    1.83
    _,
    1.75
     {},
    1.68
    ({},
    1.67
    Activations Density 0.399%

    No Known Activations