© 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. 16-GEMMASCOPE-2-RES-262K
    7. 105224
    Prev
    Next
    INDEX
    Explanations

    terms, analysis, transfer, Virtue

    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_16_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
     compds
    0.47
    𝗦
    0.45
     По
    0.45
     कंप्यूट
    0.45
    ousse
    0.45
    uze
    0.44
     opinions
    0.44
    ंपरा
    0.44
     Благодаря
    0.43
     Opinions
    0.43
    POSITIVE LOGITS
    يرات
    0.50
    า
    0.50
    رت
    0.46
    geometry
    0.45
    燃料
    0.45
    دا
    0.45
    نه
    0.45
    اين
    0.45
     blat
    0.45
    дії
    0.44
    Activations Density 0.000%

    No Known Activations