© 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. 50345
    Prev
    Next
    INDEX
    Explanations

    conditions, effects, and contexts

    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
    𝟎
    0.48
    盐
    0.48
    ０
    0.47
    Mentor
    0.47
    ഷ്ട്ര
    0.47
     час
    0.46
    ឱ
    0.46
     కేంద్ర
    0.46
    ifício
    0.45
     ০
    0.45
    POSITIVE LOGITS
    .
    0.44
     chacun
    0.42
     compared
    0.42
    すごく
    0.42
     immunity
    0.40
     were
    0.40
     paru
    0.39
     tari
    0.38
    0.38
     grup
    0.38
    Activations Density 0.005%

    No Known Activations