© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-65K
    4. 3950
    Prev
    Next
    INDEX
    Explanations

    code syntax and keywords

    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_40_width_65k_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
    কিন্ত
    0.38
    ᕇ
    0.37
    یرو
    0.35
    ্্
    0.35
     foliis
    0.35
     femora
    0.33
     بہتر
    0.33
     পরিষ
    0.33
     besucht
    0.33
    umboldt
    0.32
    POSITIVE LOGITS
    )
    0.40
    ).
    0.38
    니다
    0.37
    .
    0.37
    );
    0.37
     ignore
    0.36
    ignore
    0.35
    입니다
    0.35
    )
    0.34
    ።
    0.34
    Activations Density 0.110%

    No Known Activations