© 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. 113763
    Prev
    Next
    INDEX
    Explanations

    end or final

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

    The neuron responds to tokens that denote textual boundaries or positions (e.g. “end,” “final,” “beginning,” etc.).

    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
    through
    -2.58
    <
    -2.42
     marcada
    -2.34
     THROUGH
    -2.05
    历史上
    -1.96
     fün
    -1.95
     cruzado
    -1.95
     falando
    -1.95
     ۳
    -1.91
     cambiando
    -1.91
    POSITIVE LOGITS
    end
    2.63
    h
    2.23
    脔
    2.16
     cauſe
    2.14
    一直
    2.09
    ma
    2.08
    駸
    2.05
    𔘓
    2.02
    関西
    1.98
    prende
    1.97
    Activations Density 0.006%

    No Known Activations