© 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. 3819
    Prev
    Next
    INDEX
    Explanations

    programming language keywords & snippets

    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
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.33
     teda
    0.33
     दर
    0.33
     teilweise
    0.31
    各类
    0.30
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.30
     daí
    0.30
    厝
    0.30
     үнд
    0.29
    รือ
    0.29
    POSITIVE LOGITS
     this
    0.56
     you
    0.52
     DELLA
    0.46
     allows
    0.45
    我们需要
    0.44
     when
    0.44
    This
    0.43
    यह
    0.43
     Ketika
    0.43
     நீங்கள்
    0.42
    Activations Density 0.186%

    No Known Activations