© 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. 100457
    Prev
    Next
    INDEX
    Explanations

    states, periods, or phases

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

    This neuron detects mentions of time intervals or phases—words like “period,” “day,” “final,” “stages,” etc., that mark stages or segments of a timeline.

    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
    urés
    -1.31
     odeur
    -1.30
     you
    -1.30
     licorne
    -1.27
     Bedürfn
    -1.26
     ešte
    -1.21
    がありますが
    -1.21
     tweede
    -1.19
     noix
    -1.16
    もありますが
    -1.14
    POSITIVE LOGITS
     with
    1.58
     quindi
    1.31
     più
    1.23
    badlogic
    1.23
     where
    1.20
    ”.
    1.18
     más
    1.17
    」。
    1.13
    byes
    1.12
    these
    1.11
    Activations Density 0.111%

    No Known Activations