© 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. 59502
    Prev
    Next
    INDEX
    Explanations

    names preceding surnames or titles

    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
    a
    -3.14
    or
    -3.03
    an
    -2.89
    h
    -2.69
     They
    -2.58
    with
    -2.45
     However
    -2.38
    一つの
    -2.36
    le
    -2.34
    或
    -2.33
    POSITIVE LOGITS
    ൎ
    2.70
    栴
    2.48
    猡
    2.47
    鸸
    2.41
    ፨
    2.39
    ⮑
    2.34
    ;';
    2.33
    
    2.30
    forKey
    2.28
    pupil
    2.27
    Activations Density 0.009%

    No Known Activations