© 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. 10-GEMMASCOPE-RES-131K
    7. 60012
    Prev
    Next
    INDEX
    Explanations

    av

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

    The neuron activates on any token containing the letter sequence “av” (in either lower‐ or upper‐case).

    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
    鋮
    -2.64
     információ
    -2.34
    Особенности
    -2.33
    itecture
    -2.30
     összefoglal
    -2.27
    𖣘
    -2.27
    ጮ
    -2.23
    because
    -2.22
    .”
    -2.19
    There
    -2.19
    POSITIVE LOGITS
    av
    4.75
    ay
    3.80
    da
    3.53
    ad
    3.42
    ag
    3.20
    ak
    3.03
    ab
    3.02
    am
    2.98
    ain
    2.89
    om
    2.88
    Activations Density 0.011%

    No Known Activations