© 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. 22-GEMMASCOPE-RES-131K
    7. 72280
    Prev
    Next
    INDEX
    Explanations

    asking for specific details

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

    The neuron fires on words that assert absence or denial (e.g. “no,” “nothing,” “none,” “didn’t,” 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_22/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
     xxvi
    -0.90
     Viewer
    -0.88
     baka
    -0.84
    abaikan
    -0.84
     turist
    -0.84
    otypic
    -0.82
    зне
    -0.81
    childrens
    -0.81
     papa
    -0.78
    Comentario
    -0.78
    POSITIVE LOGITS
     specify
    1.02
     specific
    1.00
     what
    0.98
    具体
    0.95
     details
    0.94
     Are
    0.88
    具体的
    0.87
     detail
    0.85
     specifics
    0.85
     describe
    0.84
    Activations Density 0.026%

    No Known Activations