© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 30713
    Prev
    Next
    INDEX
    Explanations

    here are

    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
     breakage
    0.45
     adheres
    0.44
    >∕
    0.43
     bilayer
    0.42
     expire
    0.42
    MathML
    0.42
     adsor
    0.41
     ಈ
    0.41
     Iterate
    0.41
     analysis
    0.40
    POSITIVE LOGITS
    是一些
    0.49
     некоторое
    0.43
    illeurs
    0.42
    ofan
    0.42
    ’
    0.42
    o
    0.42
     مثلا
    0.41
     propos
    0.40
     Alguns
    0.40
     two
    0.39
    Activations Density 0.033%

    No Known Activations