© 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. 40257
    Prev
    Next
    INDEX
    Explanations

    number of

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

    This neuron primarily detects the token “numberOf” (as used in code identifiers for counts).

    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
     to
    -2.61
    毉
    -2.53
     エントランス
    -2.48
     they
    -2.45
     angepasst
    -2.42
     aktiviert
    -2.38
     poised
    -2.33
    \
    -2.31
     hinzugefügt
    -2.30
     durchgeführt
    -2.27
    POSITIVE LOGITS
    ࿚
    2.92
    咈
    2.84
    d
    2.80
    r
    2.78
    焢
    2.64
    s
    2.59
    辚
    2.59
    媖
    2.55
     facilitate
    2.45
    翃
    2.42
    Activations Density 0.000%

    No Known Activations