© 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. 34-GEMMASCOPE-RES-131K
    7. 31151
    Prev
    Next
    INDEX
    Explanations

    substituent / distributable / constitutive

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

    The neuron activates on chemical‐substituent terminology—roots like “substitu,” “substituent,” “alkyl,” “dimethyl,” etc., that denote molecular substituent groups.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    PU
    -0.81
    겟
    -0.76
     Fernández
    -0.74
     Gauthier
    -0.73
    βα
    -0.73
    issner
    -0.72
    épisode
    -0.71
    atypes
    -0.71
     Wesleyan
    -0.71
    bình
    -0.71
    POSITIVE LOGITS
    ution
    1.05
    سیون
    0.85
    cion
    0.82
    tion
    0.78
     Constitu
    0.76
    tions
    0.75
    ción
    0.73
    Constitu
    0.73
    Splits
    0.72
     انجام
    0.71
    Activations Density 0.073%

    No Known Activations