© 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. 41175
    Prev
    Next
    INDEX
    Explanations

    boiler-plate code

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron fires on hyphenated compound phrases (e.g. “bottom-line,” “boiler-plate,” “big-picture”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    </td>
    -2.34
    adalah
    -1.93
    </h5>
    -1.92
    VERY
    -1.91
    ',
    -1.88
    "));
    -1.82
    '}
    -1.81
     tijdens
    -1.80
    ",
    -1.76
    -1.74
    POSITIVE LOGITS
    er
    2.61
    man
    1.99
    F
    1.93
    R
    1.91
    H
    1.89
    N
    1.88
    Y
    1.86
    s
    1.82
    ll
    1.81
    less
    1.80
    Activations Density 0.004%

    No Known Activations