© 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. 70095
    Prev
    Next
    INDEX
    Explanations

    code with arrays

    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
    You
    -2.27
    If
    -2.09
    For
    -2.05
    There
    -2.05
    We
    -2.02
    It
    -1.99
    Other
    -1.98
    Very
    -1.84
    Your
    -1.82
    Those
    -1.80
    POSITIVE LOGITS
     a
    2.39
    ৢ
    1.90
    学的
    1.88
     sposob
    1.88
     such
    1.84
     pueden
    1.81
     gesamte
    1.80
    樒
    1.79
     pogod
    1.79
     hábit
    1.79
    Activations Density 0.002%

    No Known Activations