© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 205094
    Prev
    Next
    INDEX
    Explanations

    list, check, immediately, research, puppy

    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
     Secrets
    0.48
    商品を
    0.44
     }^{
    0.41
    ೇವೆ
    0.41
    元の
    0.41
    ၢ
    0.41
    IL
    0.41
     등의
    0.41
    ὢ
    0.41
    ವೆ
    0.40
    POSITIVE LOGITS
     الذ
    0.49
    nDims
    0.48
    Dijstra
    0.46
    শিক্ষা
    0.45
     எந்த
    0.44
    rinth
    0.44
    根本
    0.43
     pobres
    0.43
    farm
    0.43
     пробе
    0.43
    Activations Density 0.000%

    No Known Activations