© 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. 19744
    Prev
    Next
    INDEX
    Explanations

    specific technical terms

    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
    эт
    0.45
    वित्त
    0.42
    乡
    0.41
     lens
    0.41
     hometown
    0.40
     जिले
    0.40
    anian
    0.39
    ributors
    0.39
    imetre
    0.39
    ຕະ
    0.39
    POSITIVE LOGITS
     potentials
    0.46
     nextPage
    0.46
    fnamefont
    0.44
     नॉट
    0.43
     kicked
    0.43
    協
    0.43
     ಬಿಜೆಪಿ
    0.43
    ҡ
    0.43
    arlock
    0.42
     потер
    0.42
    Activations Density 0.001%

    No Known Activations