© 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. 34-GEMMASCOPE-RES-131K
    7. 91696
    Prev
    Next
    INDEX
    Explanations

    slides, presentations, or similar

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

    The neuron primarily detects numeric tokens (sequences of digits) 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_34/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
     
    -1.12
     aforementioned
    -0.98
     Despite
    -0.90
    ės
    -0.88
     Since
    -0.85
     These
    -0.85
    MÁS
    -0.85
    memberof
    -0.85
    上述
    -0.84
    кож
    -0.83
    POSITIVE LOGITS
    Slide
    1.19
    slide
    1.16
     Slides
    1.13
     slide
    1.12
     Slide
    1.12
     عنه
    1.02
    slides
    1.02
    siamo
    1.00
     två
    1.00
     slides
    1.00
    Activations Density 0.001%

    No Known Activations