© 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. 41-GEMMASCOPE-2-RES-262K
    7. 59106
    Prev
    Next
    INDEX
    Explanations

    listing words and code snippets

    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_all/layer_41_width_262k_l0_big
    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
    နဲ့
    0.44
     funkt
    0.43
     기능
    0.41
     функциона
    0.39
    ್ಧ
    0.38
     functional
    0.38
    鹵
    0.38
    ➨
    0.36
    ERS
    0.36
    व्ह
    0.36
    POSITIVE LOGITS
     tinggal
    0.38
     lightening
    0.37
     až
    0.37
     teng
    0.36
     pous
    0.36
    ित
    0.35
     pang
    0.35
     Consult
    0.35
    死
    0.35
    咨询
    0.35
    Activations Density 5.084%

    No Known Activations