© 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. 64809
    Prev
    Next
    INDEX
    Explanations

    extrapolated or based on

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

    The neuron specializes in spotting instances of “extrapolated” (including phrases like “backward extrapolated” or “tentatively extrapolated”) and related measurement‐estimation terms.

    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
     reforma
    -0.85
    会儿
    -0.80
    NGL
    -0.77
     incele
    -0.73
     adorno
    -0.73
     desmon
    -0.73
    Angelina
    -0.73
    дьми
    -0.73
    לם
    -0.72
     Jarrett
    -0.72
    POSITIVE LOGITS
     extrapolation
    4.63
     extrapolated
    3.64
     Ext
    3.52
    ext
    3.16
     экстра
    3.13
    Ext
    3.03
     extra
    2.92
     EXTR
    2.48
    EXT
    2.27
    Extra
    2.22
    Activations Density 0.108%

    No Known Activations