© 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. 113733
    Prev
    Next
    INDEX
    Explanations

    out before punctuation or certain words

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

    The neuron fires on simple past–tense verbs.

    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
    ⮜
    -1.92
    ToDisplay
    -1.91
     queridos
    -1.87
    錀
    -1.85
    Ꮄ
    -1.79
    Gründe
    -1.76
    踱
    -1.74
     Tienes
    -1.72
     Encuentra
    -1.72
     ganadores
    -1.72
    POSITIVE LOGITS
    '
    2.47
    s
    2.38
     anteriormente
    2.16
    ’
    2.14
     $
    1.91
    饪
    1.73
    },
    1.72
    不起
    1.70
    镚
    1.69
    盌
    1.67
    Activations Density 0.229%

    No Known Activations