© 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. 82104
    Prev
    Next
    INDEX
    Explanations

    quantities and speed

    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
    m
    0.47
    Boxes
    0.44
    ק
    0.44
    UL
    0.44
    แต่ละ
    0.41
    Â
    0.41
     dostęp
    0.40
    ง่าย
    0.40
     engine
    0.39
     in
    0.39
    POSITIVE LOGITS
     Susanna
    0.48
     Jehova
    0.48
     worthless
    0.48
     পারিনি
    0.45
     tiennent
    0.45
    ἲ
    0.45
    䣫
    0.45
     refugi
    0.44
    retien
    0.44
     savent
    0.43
    Activations Density 0.003%

    No Known Activations