© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 52467
    Prev
    Next
    INDEX
    Explanations

    parent and kids

    np_acts-logits-general · gemini-2.5-flash-lite

    list processing and document structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     تو
    0.55
     రా
    0.54
    otherArchive
    0.53
    '/>
    0.50
     همیشه
    0.50
     вскоре
    0.50
     hiszen
    0.49
     UPSC
    0.49
    یکه
    0.48
     insbesondere
    0.48
    POSITIVE LOGITS
    圈
    0.47
    acity
    0.45
     a
    0.43
     embarrassed
    0.43
     sna
    0.42
     tempted
    0.41
    separated
    0.40
    名の
    0.40
     tainted
    0.40
     বয়
    0.39
    Activations Density 0.000%

    No Known Activations