© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 202936
    Prev
    Next
    INDEX
    Explanations

    british style

    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
    ть
    0.53
    ı
    0.49
    랏
    0.45
     :"
    0.44
    まだまだ
    0.43
    涹
    0.43
    повід
    0.43
     associa
    0.43
    зда
    0.42
     дире
    0.42
    POSITIVE LOGITS
     Eucalyptus
    0.48
     Aucun
    0.48
     eucalyptus
    0.48
    b
    0.47
    cha
    0.47
     sama
    0.45
    orys
    0.44
     scotch
    0.43
     पानी
    0.43
    CrossRef
    0.43
    Activations Density 0.000%

    No Known Activations