© 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. 112465
    Prev
    Next
    INDEX
    Explanations

    Bene, Rene, Simone names

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

    The neuron fires on any token containing the character sequence “bene” (e.g. Bene-, benevolent, 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
     They
    -2.73
     $
    -2.72
     zwölf
    -2.69
     zwanzig
    -2.63
     Their
    -2.59
    ла
    -2.59
     anfangs
    -2.55
     quintessential
    -2.53
    他自己
    -2.52
    嶮
    -2.45
    POSITIVE LOGITS
    琑
    2.78
    🌹
    2.48
     ヶ
    2.47
    🌺
    2.45
    I
    2.44
    Any
    2.36
    If
    2.33
     古风
    2.31
     pelicula
    2.30
     内衣
    2.30
    Activations Density 0.005%

    No Known Activations