© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 63044
    Prev
    Next
    INDEX
    Explanations

    body , or from February

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

    complex classifications

    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
    த்திற்கு
    0.55
     ಕರಿ
    0.55
    čko
    0.53
    🔘
    0.52
    భ్య
    0.52
    RELATES
    0.51
    骐
    0.51
    餞
    0.49
     இந்ந
    0.49
     वेलकम
    0.49
    POSITIVE LOGITS
     to
    0.47
    ევრი
    0.45
     parts
    0.43
     i
    0.41
    でも
    0.40
     SI
    0.40
     case
    0.39
     and
    0.39
     ER
    0.39
     suffis
    0.39
    Activations Density 0.000%

    No Known Activations