© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 29153
    Prev
    Next
    INDEX
    Explanations

    finding or detecting efforts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    к
    0.58
    क्र
    0.54
    அ
    0.54
    ного
    0.52
    Из
    0.52
    1
    0.52
    По
    0.50
    Раз
    0.50
    Subscriptions
    0.50
    Ни
    0.49
    POSITIVE LOGITS
    <unused506>
    0.52
     Obrigado
    0.49
     cAMP
    0.49
     Justiça
    0.47
     Política
    0.47
     黑
    0.47
    assanam
    0.44
     насеко
    0.44
     iOS
    0.43
     beef
    0.43
    Activations Density 0.003%

    No Known Activations