© 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. 84278
    Prev
    Next
    INDEX
    Explanations

    land, regulation, or explanation for why

    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
    ્સ
    0.48
    например
    0.48
     например
    0.47
    хими
    0.46
    них
    0.46
    ').':
    0.45
    ond
    0.44
    ми
    0.44
     electrónico
    0.44
    ри
    0.43
    POSITIVE LOGITS
    恂
    0.49
    晧
    0.47
    Akt
    0.47
    訫
    0.45
    Hourly
    0.44
    NYC
    0.44
    酺
    0.44
    BUR
    0.43
    Hundreds
    0.42
    殚
    0.42
    Activations Density 0.002%

    No Known Activations