© 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. 10-GEMMASCOPE-RES-131K
    7. 8156
    Prev
    Next
    INDEX
    Explanations

    affixed to

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

    The neuron fires on unusual or low-frequency “content” tokens—e.g. code identifiers, section-heading words (like “Вопрос”), legal names, or other specialized 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_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
    {
    -3.11
    t
    -2.98
    </b>
    -2.83
    }
    -2.59
    in
    -2.50
    ”
    -2.47
    この日は
    -2.39
    ate
    -2.30
    when
    -2.27
    ｋ
    -2.27
    POSITIVE LOGITS
    ";
    2.33
     Of
    2.25
    心中
    2.17
    靨
    2.14
     Geografía
    2.11
     耐
    2.06
    。"
    2.06
     votre
    2.05
    %;
    2.03
     Produkten
    2.03
    Activations Density 0.002%

    No Known Activations