© 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. 59944
    Prev
    Next
    INDEX
    Explanations

    tunnelbear

    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
    만
    0.38
    bed
    0.37
    inent
    0.37
     prad
    0.37
    oga
    0.36
    special
    0.36
     Bragg
    0.35
    bra
    0.35
    ::~
    0.35
    dil
    0.35
    POSITIVE LOGITS
     तुर
    0.44
     entrer
    0.42
     đổi
    0.42
     लगाई
    0.42
     नियंत्र
    0.42
     répon
    0.40
     nhiêu
    0.40
     величи
    0.39
    亚博
    0.39
     quién
    0.39
    Activations Density 0.002%

    No Known Activations