© 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. 22-GEMMASCOPE-RES-131K
    7. 72709
    Prev
    Next
    INDEX
    Explanations

    manual control or tracking

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

    The neuron detects first-person self-references in text, especially “I am” and similar “I” statements.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    訝
    -0.87
     ANYONE
    -0.79
     territo
    -0.79
     exaggeration
    -0.78
    ERICAL
    -0.77
    ensos
    -0.76
    ă
    -0.76
     contactless
    -0.76
    łami
    -0.76
     unusual
    -0.75
    POSITIVE LOGITS
     manually
    1.08
     manualmente
    0.99
     pouze
    0.96
     ficar
    0.95
     selalu
    0.94
    Manually
    0.93
    ikbaar
    0.93
     manuell
    0.92
     kesulitan
    0.91
     costly
    0.90
    Activations Density 0.272%

    No Known Activations