© 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. 195970
    Prev
    Next
    INDEX
    Explanations

    lists, quotes, and family matters

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

    chemical precursors, measurements, explanations

    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
     corr
    0.47
     indic
    0.46
     Alp
    0.46
     늘
    0.45
     alpine
    0.44
     Right
    0.44
     vanaf
    0.43
     قدم
    0.43
     gezond
    0.42
     maxX
    0.42
    POSITIVE LOGITS
    Вакан
    0.54
    誰
    0.51
    歷史
    0.50
    фессиона
    0.48
    ळी
    0.48
    робнее
    0.47
    τεύ
    0.47
    ATA
    0.45
     пациен
    0.45
     desempeño
    0.45
    Activations Density 0.000%

    No Known Activations