© 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. 201864
    Prev
    Next
    INDEX
    Explanations

    show a warning

    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
    ;
    0.50
    ,
    0.49
    ete
    0.45
    )
    0.43
    is
    0.43
    are
    0.41
    :
    0.41
    ز
    0.41
    ).
    0.40
    );
    0.39
    POSITIVE LOGITS
     ഉയർന്ന
    0.50
     හොඳ
    0.45
     ඉක්
    0.45
     Bxe
    0.45
     antigüedad
    0.45
    ॉस
    0.44
    粔
    0.44
    
    0.44
     ಅತ್ಯ
    0.43
     በጥ
    0.43
    Activations Density 0.006%

    No Known Activations