© 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. 41-GEMMASCOPE-2-RES-262K
    7. 60067
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    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_all/layer_41_width_262k_l0_big
    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
     கல்
    0.45
     क्षार
    0.41
    地下
    0.40
     MAH
    0.40
    のデザイン
    0.40
    栤
    0.39
     結婚
    0.39
     管
    0.39
     CTCF
    0.38
     הה
    0.38
    POSITIVE LOGITS
    pkg
    0.47
     Seja
    0.37
    fondo
    0.36
    ционным
    0.35
     masks
    0.34
    ിയെ
    0.34
     purportedly
    0.34
     well
    0.33
     menacing
    0.33
     Pacífico
    0.33
    Activations Density 1.270%

    No Known Activations