© 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. 74486
    Prev
    Next
    INDEX
    Explanations

    sump baffle shroud dies

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

    The neuron flags specialized technical component nouns (e.g. shroud, gantries, valves, baffle) in hardware-oriented descriptions.

    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
    .
    -2.31
    ”
    -1.90
    ..”
    -1.89
    “
    -1.89
     remainder
    -1.89
    in
    -1.86
    </h3>
    -1.80
    oczes
    -1.73
    ῃ
    -1.72
    silien
    -1.71
    POSITIVE LOGITS
     "
    2.22
     of
    2.19
     '
    2.11
     the
    1.97
    '
    1.90
    尤其是
    1.90
    𝔨
    1.88
     
    1.84
     özellikle
    1.77
     embarazada
    1.75
    Activations Density 0.112%

    No Known Activations