© 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. 99417
    Prev
    Next
    INDEX
    Explanations

    at times

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

    The neuron fires strongly on the token “at” when it appears as part of a date‐time stamp (e.g. “at 12:35 PM”).

    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
    蠃
    -1.92
     appena
    -1.74
    four
    -1.68
     keempat
    -1.68
    several
    -1.64
     considerazione
    -1.63
     alcune
    -1.63
    the
    -1.61
    
    -1.59
    some
    -1.59
    POSITIVE LOGITS
    xymatrix
    1.56
     because
    1.48
     endless
    1.45
     этого
    1.45
     it
    1.43
     insanlar
    1.39
     stellar
    1.37
     limitless
    1.36
    :
    1.35
     estructuras
    1.34
    Activations Density 0.015%

    No Known Activations