© 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. 40-GEMMASCOPE-2-RES-262K
    7. 204661
    Prev
    Next
    INDEX
    Explanations

    Treasury bill

    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_40_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
     यावेळी
    0.40
    ))$,
    0.38
     крайне
    0.38
    scaler
    0.37
    害者
    0.37
    きっかけ
    0.36
    াভাব
    0.36
     تك
    0.36
    CreateTable
    0.36
     सिंग
    0.35
    POSITIVE LOGITS
     source
    0.48
    Source
    0.45
     Source
    0.43
     flank
    0.41
    源
    0.41
    source
    0.41
    ريقه
    0.41
    fron
    0.40
     sourcing
    0.39
     탄
    0.39
    Activations Density 0.000%

    No Known Activations