© 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. 113800
    Prev
    Next
    INDEX
    Explanations

    excellent qualities and performance

    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
    鹪
    -3.08
    鹛
    -2.98
     Quando
    -2.94
    瘊
    -2.88
    ೢ
    -2.84
     delightfully
    -2.83
    齪
    -2.78
    嫑
    -2.77
     deliciously
    -2.75
    蟥
    -2.75
    POSITIVE LOGITS
    0
    3.83
    .
    3.42
    Although
    3.41
    7
    3.31
    Even
    3.30
    While
    3.28
    There
    3.28
    Just
    3.23
    8
    3.22
    Also
    3.17
    Activations Density 0.004%

    No Known Activations