© 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. 120978
    Prev
    Next
    INDEX
    Explanations

    without offering

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

    betrayal or 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
    0
    0.57
    したのは
    0.48
     श्रमिक
    0.48
     են
    0.47
     हेनरी
    0.47
     मजदूर
    0.46
     अधिवक्ता
    0.46
     vuông
    0.45
    ิ
    0.45
     positif
    0.45
    POSITIVE LOGITS
     perennials
    0.42
    INE
    0.42
     preoccupation
    0.41
     neoplastic
    0.41
    iegen
    0.40
    allaitement
    0.40
    দানের
    0.40
    Naissance
    0.40
     grapes
    0.39
    щем
    0.39
    Activations Density 0.002%

    No Known Activations