© 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-65K
    7. 54949
    Prev
    Next
    INDEX
    Explanations

    repair, difference, compatibility, ethical discussion

    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_65k_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
    Бо
    0.50
    Μ
    0.49
    Па
    0.49
    М
    0.49
    Га
    0.47
    Б
    0.46
    bx
    0.46
    Ме
    0.46
    יי
    0.45
    相
    0.44
    POSITIVE LOGITS
     epidemiological
    0.49
     daher
    0.49
     mendapat
    0.48
     curfew
    0.48
    serializers
    0.47
     hordes
    0.46
     Ebola
    0.46
     glomerul
    0.46
     escuchar
    0.45
     isoniazid
    0.45
    Activations Density 0.022%

    No Known Activations