© 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. 40-GEMMASCOPE-2-RES-16K
    7. 9607
    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_40_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
     etiam
    0.57
    =
    0.51
     also
    0.50
    ni
    0.44
    र्क
    0.44
    əm
    0.43
    е
    0.43
    ຸກ
    0.43
    ubmit
    0.42
    any
    0.42
    POSITIVE LOGITS
     its
    0.66
     why
    0.62
     اهمیت
    0.54
    why
    0.50
     त्याचा
    0.50
     அதன்
    0.48
     neden
    0.48
     mengapa
    0.48
     how
    0.47
     왜
    0.47
    Activations Density 0.144%

    No Known Activations