© 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. 15173
    Prev
    Next
    INDEX
    Explanations

    3 followed by digits

    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
     څه
    0.47
    帧
    0.43
     دینے
    0.43
     bạch
    0.42
     મહ
    0.41
    CEEDINGS
    0.41
    되
    0.40
     ذریع
    0.40
     طرق
    0.40
    ς
    0.40
    POSITIVE LOGITS
     Nagano
    0.46
     Martin
    0.45
     Heaven
    0.44
     most
    0.44
     s
    0.42
     Kepler
    0.42
     Cartan
    0.42
     sava
    0.41
     Nou
    0.41
     to
    0.41
    Activations Density 0.015%

    No Known Activations