© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 72111
    Prev
    Next
    INDEX
    Explanations

    finding or calculating values

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

    The neuron activates on numeric tokens (any sequence of digits or numbers) in the text.

    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
    Oferta
    -1.02
     появится
    -1.01
    Suka
    -0.98
     μην
    -0.98
    Kamera
    -0.96
    توضیحات
    -0.96
     দে
    -0.95
     interessa
    -0.93
     понадоби
    -0.93
    次回
    -0.93
    POSITIVE LOGITS
     вдоль
    1.13
     first
    1.10
    обе
    1.09
     zunächst
    1.08
     embrague
    1.03
    ([]);
    1.02
     each
    1.02
    drag
    1.02
     Each
    1.01
    erst
    1.01
    Activations Density 0.042%

    No Known Activations