© 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. 81219
    Prev
    Next
    INDEX
    Explanations

    common errors and 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
    ឡ
    0.42
    unning
    0.42
    board
    0.40
    lined
    0.40
    č
    0.40
    š
    0.40
    כ
    0.40
     lined
    0.40
    ᅨ
    0.40
    aligned
    0.39
    POSITIVE LOGITS
    传感器
    0.51
     pelatihan
    0.46
     মল
    0.46
    akespeare
    0.45
    fieldContext
    0.43
     terapia
    0.43
     cuello
    0.43
    特效
    0.43
     防
    0.42
    ওয়্যার
    0.42
    Activations Density 0.008%

    No Known Activations