© 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. 128078
    Prev
    Next
    INDEX
    Explanations

    baguette, breakdown, control

    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
    ປັນ
    0.50
    ס
    0.50
     산업
    0.49
     אמ
    0.48
    䡃
    0.48
    اد
    0.48
     meditation
    0.47
    ส
    0.47
    垍
    0.47
     experience
    0.47
    POSITIVE LOGITS
     dostup
    0.51
    부분
    0.46
     tathapi
    0.45
    不对
    0.44
    ườn
    0.43
     bezpeč
    0.43
    ál
    0.43
     überprü
    0.42
     देता
    0.41
     kontroll
    0.41
    Activations Density 0.000%

    No Known Activations