© 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. 31900
    Prev
    Next
    INDEX
    Explanations

    court case citations

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

    The neuron activates on numeric tokens—multi‐digit numbers such as years, counts, times, or other numeric 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_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
    Fill
    -0.74
    }//
    -0.74
    STORE
    -0.71
    aturen
    -0.69
    inflammation
    -0.68
    £
    -0.68
    Duff
    -0.68
    }^{(\
    -0.67
    Œ
    -0.66
     verbose
    -0.66
    POSITIVE LOGITS
    논
    0.80
    ellan
    0.72
     Blanca
    0.70
    headless
    0.69
    rlr
    0.69
    Bara
    0.69
    τητα
    0.68
    ค้า
    0.68
    Willy
    0.67
    EREN
    0.66
    Activations Density 0.066%

    No Known Activations