© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 58918
    Prev
    Next
    INDEX
    Explanations

    work task completion

    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_10/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
    舠
    -1.38
     englisch
    -1.35
    Опыт
    -1.27
    vē
    -1.22
    𓆸
    -1.20
    辈子
    -1.19
    ꔛ
    -1.19
     ktore
    -1.17
     version
    -1.16
    梣
    -1.16
    POSITIVE LOGITS
    Sometimes
    1.47
    もちろん
    1.46
    ',
    1.45
     Тех
    1.41
     Both
    1.38
    luor
    1.35
    ffle
    1.34
     вроде
    1.34
    ни
    1.32
    Both
    1.32
    Activations Density 0.020%

    No Known Activations