© 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. 28183
    Prev
    Next
    INDEX
    Explanations

    researchgate / publication

    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
    黉
    0.43
     Felic
    0.41
    岁月
    0.40
     hjäl
    0.39
    ണ്‍
    0.38
    (-)
    0.37
     بالج
    0.37
    eline
    0.36
     Bullock
    0.36
    尉
    0.36
    POSITIVE LOGITS
    取决于
    0.44
    Gra
    0.39
    厈
    0.37
     Respiratory
    0.36
    Requires
    0.36
     requires
    0.35
    inclusive
    0.35
    ouw
    0.35
    <\
    0.35
    Respiratory
    0.35
    Activations Density 0.000%

    No Known Activations