© 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. 148878
    Prev
    Next
    INDEX
    Explanations

    legal and measurement terms

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

    future trends and detailed processes

    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
    Suspend
    0.54
     ترب
    0.51
    sunday
    0.50
    '></
    0.48
    鉄道
    0.47
     viagem
    0.47
     lundi
    0.47
     ਵਿੱਚ
    0.46
    요일
    0.44
    競技
    0.44
    POSITIVE LOGITS
    (
    0.50
     Things
    0.46
    assert
    0.46
     Trusts
    0.46
    ew
    0.46
     Lately
    0.46
    owers
    0.45
    utf
    0.45
     옳
    0.45
    awar
    0.44
    Activations Density 0.000%

    No Known Activations