© 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. 85895
    Prev
    Next
    INDEX
    Explanations

    on a regular basis

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

    The neuron activates on occurrences of the phrase “on a … basis,” i.e. frequency expressions like “on a daily basis,” “on a regular basis,” 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_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
    </td>
    -2.67
     fashioned
    -2.56
    哙
    -2.52
    齶
    -2.48
    ’)
    -2.47
     powiedział
    -2.42
     parachoque
    -2.33
    瀦
    -2.31
    ’”
    -2.28
    ciutto
    -2.27
    POSITIVE LOGITS
    in
    3.16
    可以
    3.08
    '
    3.03
    le
    2.88
    ti
    2.78
    o
    2.58
    <em>
    2.53
    This
    2.52
    你
    2.45
    f
    2.39
    Activations Density 0.010%

    No Known Activations