© 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. 73045
    Prev
    Next
    INDEX
    Explanations

    New York, Wellard

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

    The neuron specializes in detecting numeric tokens (numbers and numerical expressions, including multi-digit and decimal values).

    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
     ranting
    -1.17
    fucking
    -1.13
    wonderful
    -1.08
    horloge
    -1.05
    blah
    -1.05
    beautiful
    -1.04
    managing
    -1.04
     ick
    -1.03
    stupid
    -1.03
    crazy
    -1.03
    POSITIVE LOGITS
     this
    1.48
     priorities
    1.13
     ingenious
    1.05
     symmetry
    1.01
     не
    1.00
    Ẓ
    0.99
    只能
    0.97
     it
    0.97
    ászló
    0.97
     OGSÅ
    0.96
    Activations Density 0.023%

    No Known Activations