© 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. 10-GEMMASCOPE-RES-131K
    7. 70280
    Prev
    Next
    INDEX
    Explanations

    Embodiments of invention

    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
    of
    -1.67
    no
    -1.66
    .)
    -1.62
    v
    -1.59
    ."
    -1.55
    by
    -1.52
    so
    -1.52
    um
    -1.52
    up
    -1.51
    grandchildren
    -1.51
    POSITIVE LOGITS
    婓
    1.59
    この日
    1.51
     vagyok
    1.47
    玏
    1.45
    殁
    1.43
    　↓
    1.39
    夘
    1.39
     Здесь
    1.39
     stratég
    1.36
    𓐍
    1.36
    Activations Density 0.013%

    No Known Activations