© 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. 65293
    Prev
    Next
    INDEX
    Explanations

    laboratory procedures and quantitative measurements

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

    scientific laboratory procedures in formal experimental research contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron detects numeric tokens, i.e. numbers and measurements (including integers and decimals).

    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
     he
    -1.33
     you
    -1.27
     meskipun
    -1.21
     meski
    -1.16
    மை
    -1.11
     It
    -1.10
     字符
    -1.06
     Instead
    -1.04
     useless
    -1.02
     一九
    -1.02
    POSITIVE LOGITS
     each
    1.43
    Oby
    1.18
     آید
    1.16
     voeren
    1.16
    każ
    1.09
    sprzed
    1.07
     ペン
    1.06
     begon
    1.05
    ținut
    1.02
     chacun
    1.01
    Activations Density 0.021%

    No Known Activations