© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 12903
    Prev
    Next
    INDEX
    Explanations

    backgrounds, history, achievements, or track record

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

    biographical history and experience

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    able
    0.53
    be
    0.52
    to
    0.50
    ie
    0.49
    it
    0.48
    O
    0.47
    BAR
    0.47
    R
    0.47
    B
    0.47
    api
    0.46
    POSITIVE LOGITS
     accomplishments
    0.88
     achievements
    0.73
     biographical
    0.73
     antecedentes
    0.71
     биографи
    0.69
     backstory
    0.69
     geçmiş
    0.68
    Achievements
    0.68
     trayectoria
    0.68
    実績
    0.68
    Activations Density 0.064%

    No Known Activations