© 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-65K
    7. 49523
    Prev
    Next
    INDEX
    Explanations

    handle contextual information

    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_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
     მომ
    0.46
    сто
    0.42
    ubi
    0.41
    厛
    0.41
    માં
    0.40
     trif
    0.40
     에서
    0.39
    汹
    0.39
    enet
    0.38
    ရန်
    0.37
    POSITIVE LOGITS
    imetype
    0.37
     ello
    0.37
     заключа
    0.36
     forme
    0.36
     flanges
    0.36
     بول
    0.36
    ikte
    0.35
    ቕ
    0.35
     liners
    0.35
     ell
    0.35
    Activations Density 0.004%

    No Known Activations