© 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-262K
    7. 12466
    Prev
    Next
    INDEX
    Explanations

    service / above / next

    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_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
     \
    0.43
     \\
    0.40
     ‌
    0.37
     horizontal
    0.36
     மற்றும்
    0.35
     {
    0.35
     Hi
    0.35
     ж
    0.35
     -.
    0.34
     Horizontal
    0.34
    POSITIVE LOGITS
    ospels
    0.43
     lasciato
    0.40
    ropath
    0.38
    ोजित
    0.38
    कियों
    0.38
     Pied
    0.38
     vehement
    0.37
    ायदे
    0.37
    াবাদী
    0.37
    粲
    0.37
    Activations Density 0.004%

    No Known Activations