© 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. 76011
    Prev
    Next
    INDEX
    Explanations

    Python installation, Windows setup

    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
     ORGAN
    0.52
     rupani
    0.46
    ंत
    0.46
    coded
    0.46
    슌
    0.45
    ν
    0.44
    thats
    0.43
    ᄍ
    0.43
    ன்ஸ்
    0.42
     ప్రముఖ
    0.42
    POSITIVE LOGITS
     یا
    0.53
     Veterinary
    0.48
     sostit
    0.46
     Grant
    0.46
     desse
    0.46
     Dermatology
    0.44
     Len
    0.43
     Field
    0.43
     Occupational
    0.42
     Fighter
    0.41
    Activations Density 0.007%

    No Known Activations