© 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. 31-GEMMASCOPE-2-RES-262K
    7. 128723
    Prev
    Next
    INDEX
    Explanations

    discussion stems from

    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_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
     μπορού
    0.44
    КИ
    0.42
    રિ
    0.42
    קה
    0.42
    exempl
    0.42
    罅
    0.41
    一度
    0.40
     tavolo
    0.40
    пети
    0.40
    РИ
    0.39
    POSITIVE LOGITS
     বাংলায়
    0.43
     Gases
    0.42
     overstated
    0.41
     Treats
    0.41
     treats
    0.40
    Bug
    0.40
    s
    0.40
     Words
    0.40
     Converts
    0.40
     항상
    0.39
    Activations Density 0.001%

    No Known Activations