© 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. 201580
    Prev
    Next
    INDEX
    Explanations

    phrase structure and description

    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
    är
    0.47
     કરતા
    0.44
     ጉዳ
    0.42
     નીચે
    0.42
     caster
    0.42
    係る
    0.41
    ).*
    0.41
     иң
    0.41
     holotype
    0.41
     napkin
    0.40
    POSITIVE LOGITS
    了他
    0.47
     semua
    0.45
    blogs
    0.44
    ўцаў
    0.42
     sosial
    0.41
     sein
    0.41
     kunst
    0.40
     SOUND
    0.40
    ’
    0.39
    اص
    0.39
    Activations Density 0.002%

    No Known Activations