© 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. 144239
    Prev
    Next
    INDEX
    Explanations

    specific qualifiers

    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
    сения
    0.40
    志森
    0.38
    르고
    0.37
    बारा
    0.37
    Postfix
    0.36
    ᔾ
    0.36
    があり
    0.36
    ᒋ
    0.36
    ᇁ
    0.36
    भग
    0.35
    POSITIVE LOGITS
    같은
    0.41
     Fleurit
    0.41
     Aynı
    0.40
    šću
    0.39
    oky
    0.39
     kuidas
    0.39
    വുമായ
    0.38
    ’’
    0.38
     変
    0.38
    此事
    0.38
    Activations Density 0.104%

    No Known Activations