© 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. 22-GEMMASCOPE-RES-131K
    7. 38612
    Prev
    Next
    INDEX
    Explanations

    Q: or GM:

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

    The neuron activates on numeric literals (i.e. standalone numbers and size constants).

    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
    ubt
    -1.29
     FIFTH
    -1.19
    yyj
    -1.16
     každý
    -1.15
     REVOLUTION
    -1.14
     xadrez
    -1.12
     menyen
    -1.10
    beginning
    -1.09
     Dinas
    -1.08
     sooo
    -1.08
    POSITIVE LOGITS
     IN
    1.23
     amusing
    1.19
     enhancing
    1.18
     which
    1.16
     but
    1.15
    !
    1.14
    اذ
    1.14
     probably
    1.13
     fascinating
    1.13
     lengthy
    1.12
    Activations Density 0.000%

    No Known Activations