© 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. 40-GEMMASCOPE-2-RES-262K
    7. 4272
    Prev
    Next
    INDEX
    Explanations

    redirection, translation, speech

    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_40_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
    ăți
    0.34
    鯉
    0.34
    icolored
    0.33
    andaş
    0.33
     Muitos
    0.33
    éal
    0.33
    둑
    0.33
     কিওয়ার্ড
    0.33
     أجل
    0.33
     paylaş
    0.32
    POSITIVE LOGITS
    연
    0.32
    О
    0.32
    PRO
    0.32
    cors
    0.31
     PE
    0.30
     버
    0.30
    PEZ
    0.30
    越
    0.29
    Ва
    0.29
    해보
    0.29
    Activations Density 0.000%

    No Known Activations