© 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. 143341
    Prev
    Next
    INDEX
    Explanations

    arctic, brown, week, async, blog, mojo

    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
     displaystyle
    0.43
    П
    0.43
    The
    0.43
    ount
    0.41
     Folge
    0.41
    ↵
    0.40
     ans
    0.40
    ោយ
    0.40
     de
    0.40
     managed
    0.40
    POSITIVE LOGITS
     שא
    0.54
    앱
    0.46
    欴
    0.45
    ERVER
    0.44
     न्याय
    0.43
     מה
    0.43
    }^{+},
    0.43
    犾
    0.43
    汼
    0.42
     perfecta
    0.42
    Activations Density 0.000%

    No Known Activations