© 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. 44108
    Prev
    Next
    INDEX
    Explanations

    definite + specific qualities

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

    The neuron is keyed to spotting the adjective “definite” (e.g. in “definite integral,” “definite time,” 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
    <
    -3.17
     нескольких
    -3.11
    薆
    -2.83
     dismal
    -2.69
    cargador
    -2.67
     jezt
    -2.56
     exceedingly
    -2.50
    鬭
    -2.48
     berühm
    -2.48
     três
    -2.47
    POSITIVE LOGITS
    ⸒
    3.19
    ꔛ
    2.84
    ～」
    2.84
     beslu
    2.63
    ?」
    2.58
    !”
    2.58
    .”
    2.52
     gắng
    2.50
    𓄹
    2.45
    月初
    2.44
    Activations Density 0.003%

    No Known Activations