© 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. 135711
    Prev
    Next
    INDEX
    Explanations

    creating/predicting processes

    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
     swipes
    0.49
    仩
    0.48
    欳
    0.46
     bø
    0.45
    ès
    0.45
    ুহ
    0.45
    ดื่ม
    0.45
     TIPS
    0.45
    imageId
    0.45
    骷
    0.45
    POSITIVE LOGITS
    germ
    0.44
    psi
    0.43
     costitu
    0.42
    ↵↵
    0.42
    M
    0.40
    TestCase
    0.40
    рку
    0.40
    KS
    0.40
    printing
    0.40
    cfp
    0.40
    Activations Density 0.001%

    No Known Activations