© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 36365
    Prev
    Next
    INDEX
    Explanations

    specific names and classifications

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

    The neuron activates on numeric tokens representing decimal values (numbers with a decimal point).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     аромат
    -1.25
    となりました
    -1.14
    setContentType
    -1.13
    jęcie
    -1.13
     pungkasnya
    -1.10
    ૉ
    -1.09
    ınıza
    -1.09
     шокола
    -1.09
     рецепта
    -1.09
     Estos
    -1.09
    POSITIVE LOGITS
     Unterrichts
    1.05
    టి
    1.05
    oczes
    1.03
    ⅛
    1.02
    記載
    1.02
    καν
    1.01
     tots
    0.96
     Pfar
    0.96
     briefly
    0.93
    fla
    0.92
    Activations Density 0.000%

    No Known Activations