© 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-16K
    7. 7348
    Prev
    Next
    INDEX
    Explanations

    why and how

    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_16k_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
     Lack
    0.43
     stir
    0.41
     strands
    0.41
     ε
    0.40
     inconsider
    0.39
     gour
    0.38
     Other
    0.38
     নেন
    0.38
     ર
    0.38
     kel
    0.38
    POSITIVE LOGITS
    why
    0.77
    how
    0.73
     HOW
    0.72
     cómo
    0.71
     എങ്ങനെ
    0.71
     why
    0.70
    WHY
    0.69
     how
    0.68
    Why
    0.67
     WHY
    0.65
    Activations Density 0.427%

    No Known Activations