© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 57552
    Prev
    Next
    INDEX
    Explanations

    auditioning for roles

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

    The neuron fires on terms referring to auditions or casting (e.g. “audition,” “auditions,” “casting,” “auditioned”).

    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
    vantaged
    -2.45
    袛
    -2.20
    Zubereitung
    -2.20
    and
    -2.19
    when
    -2.17
    as
    -2.17
    ’:
    -2.17
    :「
    -2.16
    así
    -2.16
    indest
    -2.13
    POSITIVE LOGITS
    ↵↵
    4.06
    {
    3.23
    ers
    2.84
    </b>
    2.84
    $
    2.67
    --
    2.56
    '
    2.55
    }$.
    2.50
    --"
    2.47
    }
    2.38
    Activations Density 0.002%

    No Known Activations