© 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-65K
    7. 12435
    Prev
    Next
    INDEX
    Explanations

    communities, timeframe

    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_65k_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
    !
    0.40
    。
    0.38
     wró
    0.35
     фонбет
    0.34
     చేస్త
    0.34
    ！】
    0.34
     تھی۔
    0.34
    ။
    0.34
     ።
    0.33
     настоящий
    0.33
    POSITIVE LOGITS
    Allows
    0.44
     taxonom
    0.44
     wikip
    0.43
     desirous
    0.41
     permettant
    0.40
    䚯
    0.40
    Meas
    0.40
    ൧
    0.39
    Aunque
    0.39
     categorization
    0.39
    Activations Density 0.046%

    No Known Activations