© 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. 7822
    Prev
    Next
    INDEX
    Explanations

    words starting with min

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

    The neuron never activates on any of the provided tokens, indicating it’s effectively inactive (dead) on these inputs.

    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
    勠
    -2.09
    </h5>
    -1.99
     in
    -1.95
    噚
    -1.75
     all
    -1.66
    ၠ
    -1.66
    ஂ
    -1.65
     from
    -1.62
    嚳
    -1.62
    ꠥ
    -1.61
    POSITIVE LOGITS
    氿
    2.05
     to
    1.95
    翃
    1.84
     but
    1.74
    actually
    1.71
    蕺
    1.66
     realmente
    1.66
    ܆
    1.64
    ーーーー
    1.61
    を終
    1.59
    Activations Density 0.000%

    No Known Activations