© 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. 91195
    Prev
    Next
    INDEX
    Explanations

    patterns in lists

    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
     congenial
    0.48
     powerfully
    0.45
     pirm
    0.45
     lore
    0.45
    상
    0.45
     referencia
    0.44
     indulgence
    0.44
    良
    0.44
    流
    0.44
    ונה
    0.43
    POSITIVE LOGITS
     আধুনিক
    0.47
    printk
    0.46
     합니다
    0.43
    ๐
    0.42
     comptes
    0.42
     Н
    0.41
     하지만
    0.41
     Ч
    0.40
     প্রতিদিন
    0.40
     আমর
    0.40
    Activations Density 0.001%

    No Known Activations