© 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. 58954
    Prev
    Next
    INDEX
    Explanations

    SIMP, NSP, or NECESSITATING

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

    The neuron detects the character sequence “simp” (i.e. the start of words like simple, simplistic, simplifier, 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
    焄
    -3.22
     But
    -2.94
    谖
    -2.86
    Ꮟ
    -2.78
     estrateg
    -2.73
    瑨
    -2.50
    Donativos
    -2.48
    摃
    -2.42
    เกง
    -2.36
    桕
    -2.34
    POSITIVE LOGITS
    a
    3.39
     avec
    3.06
    橚
    2.67
    the
    2.56
    周囲
    2.48
     הוא
    2.42
     takimi
    2.36
    𔘓
    2.36
     出来
    2.36
    }{
    2.34
    Activations Density 0.008%

    No Known Activations