© 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. 16-GEMMASCOPE-2-RES-65K
    7. 2331
    Prev
    Next
    INDEX
    Explanations

    (Critical) or (Vibe:

    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_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
    ون
    0.57
    ان
    0.57
    an
    0.51
    ه
    0.50
    ע
    0.46
    ன்
    0.45
    ни
    0.45
    માં
    0.44
    وم
    0.43
    نا
    0.43
    POSITIVE LOGITS
     to
    0.54
     is
    0.53
     I
    0.49
     $
    0.46
     of
    0.45
    0.40
    ч
    0.38
    ?
    0.35
    -
    0.35
     (
    0.34
    Activations Density 0.524%

    No Known Activations