© 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-262K
    7. 37965
    Prev
    Next
    INDEX
    Explanations

    incorporating into the

    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
     многи
    0.47
    ཥ
    0.47
     birçok
    0.46
    讓人
    0.45
     ఎవ
    0.44
    ට්ට
    0.44
     внед
    0.44
    騏
    0.44
    鐧
    0.44
     ذہن
    0.44
    POSITIVE LOGITS
     oblivion
    0.44
    this
    0.43
     marad
    0.43
    thyl
    0.41
     Vá
    0.41
    wh
    0.41
    의
    0.40
     emptiness
    0.40
    นี้
    0.39
     amyl
    0.39
    Activations Density 0.001%

    No Known Activations