© 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. 72378
    Prev
    Next
    INDEX
    Explanations

    claims, manufacturers, firms, data, upload

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

    12th century, milliseconds

    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
     ולא
    0.48
    ENDAR
    0.48
    ר
    0.47
    MONTH
    0.47
    FALSE
    0.46
    timestamp
    0.46
    r
    0.45
     RULE
    0.45
     FALSE
    0.43
    ୋ
    0.43
    POSITIVE LOGITS
    Ꮘ
    0.43
    িত্তিক
    0.43
     сигна
    0.43
     Bhuv
    0.42
     বলেছে
    0.42
    userManager
    0.42
     मिरर
    0.41
    ئة
    0.40
     জানিয়েছে
    0.40
    йи
    0.40
    Activations Density 0.000%

    No Known Activations