© 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. 112354
    Prev
    Next
    INDEX
    Explanations

    expressing opinions

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

    This neuron responds to first‐person expressions of fear or being scared (e.g. “I was scared ...”).

    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
     is
    -1.24
     Interestingly
    -1.20
     According
    -1.17
     I
    -1.14
     include
    -1.13
     Evidently
    -1.13
    LISTS
    -1.12
     Apparently
    -1.10
     Other
    -1.09
     Whether
    -1.09
    POSITIVE LOGITS
     нашим
    1.36
     그리고
    1.24
     prachtig
    1.24
    Cef
    1.23
    会导致
    1.22
     вдох
    1.20
    laß
    1.19
     Pamph
    1.18
     mää
    1.17
     geweldig
    1.17
    Activations Density 0.070%

    No Known Activations