© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27366
    Prev
    Next
    INDEX
    Explanations

    HTML element tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vienas
    -1.09
    nologia
    -1.09
     nowa
    -1.07
     fekete
    -1.06
    máy
    -1.05
     ส์
    -1.04
     мужская
    -1.04
    ppo
    -1.04
    eurs
    -1.03
    trường
    -1.02
    POSITIVE LOGITS
     with
    0.95
     it
    0.94
     and
    0.90
     boasts
    0.86
     aptly
    0.85
    4
    0.84
    終わり
    0.84
    経緯
    0.84
    As
    0.82
    If
    0.81
    Activations Density 0.001%

    No Known Activations