© 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. 31-GEMMASCOPE-2-RES-65K
    7. 46789
    Prev
    Next
    INDEX
    Explanations

    messy, costly, or obvious

    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_31_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
    দুই
    0.44
     taiwan
    0.40
    ⛎
    0.40
    btw
    0.40
     jd
    0.39
     Pern
    0.38
    tble
    0.37
     btw
    0.37
     पश्चिमी
    0.37
     मरा
    0.37
    POSITIVE LOGITS
     caractér
    0.40
    ≫
    0.37
    觀察
    0.36
    ϋ
    0.36
     definidas
    0.36
    种
    0.36
    Couldn
    0.35
    鏉
    0.35
    грамма
    0.35
     gerekli
    0.35
    Activations Density 0.003%

    No Known Activations