© 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. 34-GEMMASCOPE-RES-131K
    7. 107964
    Prev
    Next
    INDEX
    Explanations

    at followed by time or condition

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

    This neuron activates on occurrences of “At” introducing list‐style or instruction phrases (e.g. “At your disposal,” “At any choice,” “At freezing temperatures,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     taas
    -0.86
     asti
    -0.84
    因为
    -0.80
    หรือ
    -0.79
    CAPTCHA
    -0.77
     quadros
    -0.77
     kapas
    -0.77
    ных
    -0.76
    แนะนำ
    -0.76
     rj
    -0.75
    POSITIVE LOGITS
     moo
    0.85
    скаго
    0.84
    マイナス
    0.83
    andowski
    0.82
    imageio
    0.79
    phylo
    0.79
     XI
    0.78
     moderate
    0.77
    ','
    0.77
    etal
    0.76
    Activations Density 0.012%

    No Known Activations