© 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. 8338
    Prev
    Next
    INDEX
    Explanations

    val, gart, fra, med, vol, ഹ

    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
    ੁ
    0.32
    是
    0.32
    凭
    0.31
    给人
    0.30
     اتار
    0.29
     চাঁদপুর
    0.29
    指出
    0.28
     الجزائر
    0.28
    偪
    0.28
    佗
    0.28
    POSITIVE LOGITS
     in
    0.35
    /-
    0.32
     for
    0.30
     vulnerability
    0.30
    ষ্টা
    0.30
     cycles
    0.30
    1
    0.30
    ل
    0.29
    7
    0.29
     cons
    0.29
    Activations Density 0.037%

    No Known Activations