© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103230
    Prev
    Next
    INDEX
    Explanations

    comma-separated lists

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

    The neuron never fires on any of these tokens—it does not detect any pattern in the presented examples.

    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
    ʯ
    -1.19
     the
    -1.18
    ditionally
    -1.15
    ܖ
    -1.13
     كمان
    -1.12
    耵
    -1.11
     επίσης
    -1.09
    obviously
    -1.09
     évidemment
    -1.09
    necessary
    -1.09
    POSITIVE LOGITS
     -
    1.42
    遨
    1.34
     even
    1.33
     (
    1.27
    話が
    1.26
     Beine
    1.25
     —
    1.24
     would
    1.23
     pocas
    1.22
     maybe
    1.17
    Activations Density 0.160%

    No Known Activations