© 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. 141372
    Prev
    Next
    INDEX
    Explanations

    gift certificate, relevant information, your comments

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

    for ... pick up

    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
    Negative Logits
    Dal
    0.51
     달
    0.50
     bienn
    0.46
    哗
    0.46
     biodivers
    0.46
    分别是
    0.46
    淀
    0.45
    晠
    0.45
     filter
    0.45
    Shah
    0.43
    POSITIVE LOGITS
     ವೈ
    0.56
    cj
    0.54
    scales
    0.53
     andro
    0.53
    c
    0.51
    ong
    0.50
    uin
    0.50
    emotion
    0.50
    onin
    0.49
    filenames
    0.49
    Activations Density 0.000%

    No Known Activations