© 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. 47937
    Prev
    Next
    INDEX
    Explanations

    recreate, heart, credit

    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
    s
    0.63
     science
    0.48
    b
    0.48
    _
    0.47
     livestock
    0.47
     skills
    0.46
     from
    0.45
     in
    0.45
    t
    0.45
     puerto
    0.44
    POSITIVE LOGITS
     तमाम
    0.55
    ölf
    0.51
     ಯಾವುದೇ
    0.50
    ຶ່ງ
    0.50
    ൮
    0.49
     важных
    0.49
    ুস
    0.49
    convén
    0.49
    AudioAsset
    0.49
     אטאטורק
    0.49
    Activations Density 0.006%

    No Known Activations