© 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. 22-GEMMASCOPE-RES-131K
    7. 26983
    Prev
    Next
    INDEX
    Explanations

    U.S. Pat. No

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

    The neuron selectively activates on numeric tokens (e.g. standalone digits, percentages, and measurements) in technical 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
    罍
    -1.30
     ſi
    -1.21
    ˂
    -1.16
     décisions
    -1.16
    droj
    -1.14
    ፲
    -1.14
    醍
    -1.12
     เร
    -1.11
     herencia
    -1.06
     แท
    -1.03
    POSITIVE LOGITS
     both
    1.46
     different
    1.40
     various
    1.38
     containing
    1.36
     primarily
    1.27
     contain
    1.23
     contains
    1.22
    ).
    1.22
     particular
    1.20
     certain
    1.15
    Activations Density 0.111%

    No Known Activations