© 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. 15252
    Prev
    Next
    INDEX
    Explanations

    programming language instantiation keywords

    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
    e
    -1.84
    y
    -1.80
    2
    -1.70
    es
    -1.66
    In
    -1.53
    只能
    -1.50
    或
    -1.42
    To
    -1.41
    t
    -1.38
    或者
    -1.38
    POSITIVE LOGITS
     and
    1.75
     such
    1.70
    ਠ
    1.65
    thâu
    1.57
     أيضًا
    1.48
    踫
    1.47
     οποία
    1.47
    itieren
    1.45
    齜
    1.44
    </sup>
    1.43
    Activations Density 0.002%

    No Known Activations