© 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. 53854
    Prev
    Next
    INDEX
    Explanations

    practical considerations

    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
    ودی
    0.48
    े
    0.46
     राव
    0.44
     Testosterone
    0.44
     ச
    0.44
     감소
    0.43
    獲得
    0.42
    össä
    0.42
    らし
    0.42
     গান্ধী
    0.41
    POSITIVE LOGITS
    loaf
    0.47
     Prepare
    0.43
     Merci
    0.42
     investigate
    0.41
    queeze
    0.40
    🅻
    0.40
     完成
    0.40
    υγ
    0.40
     पानी
    0.39
     必要
    0.39
    Activations Density 0.001%

    No Known Activations