© 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. 10-GEMMASCOPE-RES-131K
    7. 20936
    Prev
    Next
    INDEX
    Explanations

    names and technical terms

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

    The neuron activates on isolated, domain‐specific proper nouns or technical terms (e.g. product names, class names, species names).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     остальных
    -2.34
    。”
    -2.27
     такую
    -2.23
    这样
    -2.17
    𔘓
    -2.16
    X
    -2.16
    䛗
    -2.16
    用
    -2.14
    饪
    -2.09
    j
    -2.06
    POSITIVE LOGITS
    ი
    3.09
    阄
    2.27
     fün
    2.27
    <i>
    2.17
    缡
    2.16
     Betracht
    2.16
    轳
    2.16
     zwanzig
    2.14
     zwölf
    2.08
     misschien
    2.06
    Activations Density 0.000%

    No Known Activations