© 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. 199778
    Prev
    Next
    INDEX
    Explanations

    multi-language "more" or negations

    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
    ure
    0.49
     conditioned
    0.45
     commended
    0.44
    iony
    0.43
    q
    0.43
    tt
    0.43
     represented
    0.43
    ury
    0.43
     deeds
    0.43
    tti
    0.42
    POSITIVE LOGITS
    삭제
    0.49
     daugiau
    0.49
    bés
    0.47
    lıkla
    0.47
    بية
    0.46
    Pourquoi
    0.46
     więcej
    0.45
     અથ
    0.44
     schneller
    0.44
     더
    0.44
    Activations Density 0.000%

    No Known Activations