© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 21384
    Prev
    Next
    INDEX
    Explanations

    giveaway or unanswered questions

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

    The neuron fires most strongly on “giveaway”-type promotional terms (e.g. “giveaway,” “Enter to win,” etc.).

    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
    )
    -3.86
    ]
    -2.95
    {
    -2.91
    ”
    -2.86
    t
    -2.86
    ."
    -2.84
    -
    -2.73
    0
    -2.67
    \\
    -2.58
     The
    -2.56
    POSITIVE LOGITS
     and
    3.22
    鰾
    2.67
    fiable
    2.55
    嗵
    2.53
    澇
    2.45
     manajemen
    2.33
    vantaged
    2.28
     verbinding
    2.25
    uride
    2.25
     gezondheid
    2.23
    Activations Density 0.001%

    No Known Activations