© 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. 107846
    Prev
    Next
    INDEX
    Explanations

    photos, bookmarks, investments, heart

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

    rank or rate responses

    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
     showcased
    0.54
    ちょ
    0.51
    🏳
    0.47
    ዴ
    0.46
    頑張
    0.46
     fanbase
    0.45
     behest
    0.45
     showcase
    0.45
    範囲
    0.44
     shrugged
    0.44
    POSITIVE LOGITS
     或
    0.52
     或者
    0.50
     অথবা
    0.48
    iis
    0.48
    noe
    0.48
    ith
    0.47
     nDims
    0.47
    理
    0.47
     अथवा
    0.46
    㸸
    0.46
    Activations Density 0.001%

    No Known Activations