© 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. 127480
    Prev
    Next
    INDEX
    Explanations

    languages or scripts

    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
    i
    0.54
    ي
    0.51
    ت
    0.50
    Ir
    0.46
    بس
    0.45
    moder
    0.45
    neutral
    0.44
    तुर
    0.44
    ة
    0.44
    más
    0.44
    POSITIVE LOGITS
     Προ
    0.53
     ומ
    0.45
     Ры
    0.45
     পদ্ধতি
    0.45
     ച
    0.44
     Yesu
    0.44
     منهج
    0.44
     చేస్తున్న
    0.43
    を使用した
    0.42
     መንገድ
    0.42
    Activations Density 0.003%

    No Known Activations