© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 135061
    Prev
    Next
    INDEX
    Explanations

    particle physics analysis

    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
    Rab
    0.43
    💲
    0.40
    ABC
    0.39
     Corv
    0.38
     fractions
    0.38
     Corb
    0.38
    Transcription
    0.38
    abas
    0.37
     இல்லாத
    0.37
    交易所
    0.37
    POSITIVE LOGITS
     anál
    0.42
     அட
    0.40
     dg
    0.40
     maquin
    0.38
     ό
    0.38
    呜
    0.38
    锵
    0.38
     analiz
    0.38
     μή
    0.38
     análisis
    0.37
    Activations Density 0.003%

    No Known Activations