© 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. 86402
    Prev
    Next
    INDEX
    Explanations

    length/time scales

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

    The neuron activates on terms specifying measurement scales or dimensions (e.g. “length scale,” “time scales,” “nanometer scales,” “small‐scale”).

    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
     ícones
    -1.70
     défendre
    -1.68
     holz
    -1.68
     them
    -1.66
     xay
    -1.64
     frauen
    -1.63
     downloaden
    -1.61
    踯
    -1.60
     trabalhadores
    -1.59
     interesses
    -1.58
    POSITIVE LOGITS
     —
    1.58
     задач
    1.54
     $
    1.51
     الجسم
    1.43
    ']
    1.43
     */
    1.38
    توضیحات
    1.36
     Süden
    1.34
     (
    1.34
     всех
    1.34
    Activations Density 0.029%

    No Known Activations