© 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. 34297
    Prev
    Next
    INDEX
    Explanations

    code and technical descriptions

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

    The neuron responds strongly to the standalone dot (“.”) punctuation token used as a separator or full stop.

    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
     ۱۰
    -1.06
    ANGEL
    -1.05
     <<<<<<<<<<<<<<
    -1.04
     ganhou
    -1.02
    waitKey
    -1.01
     nasceu
    -0.99
     ۱۲
    -0.99
    tonsoft
    -0.98
     desn
    -0.98
     last
    -0.97
    POSITIVE LOGITS
     that
    1.06
     often
    1.02
    (*^^
    0.98
     zodat
    0.98
     zoveel
    0.96
     greatly
    0.94
     such
    0.92
    飒
    0.92
    (^_^;)
    0.92
     cannot
    0.91
    Activations Density 0.002%

    No Known Activations