© 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. 44851
    Prev
    Next
    INDEX
    Explanations

    measurement, code, hardware, and collaboration

    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
     ነው።
    0.44
     подробно
    0.43
     alakalı
    0.42
     డా
    0.42
     poskyt
    0.40
     comprim
    0.40
    ۔
    0.40
     목
    0.39
     agrade
    0.39
     🙏
    0.39
    POSITIVE LOGITS
    وء
    0.49
     receptors
    0.45
     committees
    0.44
     STRA
    0.44
    誅
    0.43
     hatched
    0.41
     brownies
    0.41
     clientèle
    0.41
    cookies
    0.40
     strains
    0.40
    Activations Density 0.001%

    No Known Activations