© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 12631
    Prev
    Next
    INDEX
    Explanations

    Manny Puig, Great Osage, # This, US struggles, Prepare to

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

    This neuron responds to the digits in subtitle‐style time-codes (e.g. the “0:0:45,245” timestamp markers).

    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
     verbe
    -1.37
     lampe
    -1.37
     plafon
    -1.36
     bolsos
    -1.28
     servis
    -1.28
     pérd
    -1.28
     sés
    -1.26
     montr
    -1.25
     bronz
    -1.25
     palme
    -1.24
    POSITIVE LOGITS
    G
    1.13
     L
    1.12
    O
    1.11
    L
    1.09
    ing
    1.09
    C
    1.08
    J
    1.07
    R
    1.06
    N
    1.05
    g
    1.05
    Activations Density 0.000%

    No Known Activations