© 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. 217821
    Prev
    Next
    INDEX
    Explanations

    largest distributors

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

    conversations and learning

    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
    exp
    0.52
    ר
    0.50
     কাউকে
    0.50
    drugs
    0.50
    Exp
    0.48
    drug
    0.48
    р
    0.48
    פ
    0.48
    Abs
    0.48
    coherent
    0.48
    POSITIVE LOGITS
     Campground
    0.52
     Barlow
    0.51
     Education
    0.47
     Asheville
    0.47
     Cidade
    0.46
     waa
    0.46
     Lyle
    0.46
     Kauai
    0.45
    igslist
    0.45
    었습니다
    0.45
    Activations Density 0.000%

    No Known Activations