© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 47921
    Prev
    Next
    INDEX
    Explanations

    @ mentions

    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
     Diving
    0.38
     Listings
    0.37
    )(\
    0.37
    <0xB4>
    0.37
     (`
    0.36
     organ
    0.36
    ctomy
    0.36
     anastomosis
    0.36
     transpose
    0.35
     Associ
    0.34
    POSITIVE LOGITS
    ovať
    0.48
     половины
    0.45
     اینجا
    0.45
    ively
    0.44
    mě
    0.44
    れない
    0.44
     всі
    0.43
     पड़ेगा
    0.43
    𒋫
    0.43
    мо
    0.43
    Activations Density 0.003%

    No Known Activations