© 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. 10384
    Prev
    Next
    INDEX
    Explanations

    even when fictional

    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
    绎
    0.51
    เลย
    0.50
     ανάπτυ
    0.50
    Continuous
    0.49
     udvik
    0.47
    அ
    0.47
    ਫ਼
    0.44
    发展
    0.43
    ด้อ
    0.43
     ontwikkeling
    0.43
    POSITIVE LOGITS
    schema
    0.45
    MediaType
    0.45
     flax
    0.44
    hiyan
    0.43
    cssMode
    0.43
    之类的
    0.43
    typeof
    0.42
    yaw
    0.42
    scrollY
    0.42
    srand
    0.42
    Activations Density 0.002%

    No Known Activations