© 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. 110327
    Prev
    Next
    INDEX
    Explanations

    building blocks and neurons

    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
     inoxyd
    0.54
    이니까
    0.53
     chromospheric
    0.52
     valable
    0.50
    ține
    0.47
     Workshops
    0.47
    今後の
    0.47
    苌
    0.46
    ίας
    0.45
     Buildable
    0.45
    POSITIVE LOGITS
    و
    0.54
     n
    0.52
     ن
    0.50
     v
    0.48
    <0x98>
    0.47
     sex
    0.45
    be
    0.45
     teaching
    0.45
    ح
    0.45
    sex
    0.45
    Activations Density 0.001%

    No Known Activations