© 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. 113522
    Prev
    Next
    INDEX
    Explanations

    next time I

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

    The neuron fires on personal pronouns—especially “I,” “you,” and their contractions (e.g. “I’m,” “you’re”).

    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
     that
    -2.06
    }$
    -1.69
     každého
    -1.66
     until
    -1.66
    ꒥
    -1.66
    IVERY
    -1.65
    烁
    -1.64
    攫
    -1.59
    nze
    -1.57
    そのため
    -1.56
    POSITIVE LOGITS
    as
    2.61
    v
    2.14
    li
    2.13
    at
    1.96
    to
    1.94
    ra
    1.94
    ya
    1.91
    u
    1.91
    焢
    1.89
    ina
    1.87
    Activations Density 0.021%

    No Known Activations