© 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. 112981
    Prev
    Next
    INDEX
    Explanations

    lack of

    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
    :
    -1.61
    聳
    -1.56
    ⁛
    -1.53
    驟
    -1.52
    我們的
    -1.47
    但这
    -1.47
    )
    -1.47
     słoń
    -1.45
    看了一眼
    -1.45
    駱
    -1.44
    POSITIVE LOGITS
     quindi
    1.70
     затем
    1.59
    ánicas
    1.52
    t
    1.52
     then
    1.45
     berbagai
    1.44
    荑
    1.43
    揼
    1.43
     sekitar
    1.38
     généralement
    1.36
    Activations Density 0.017%

    No Known Activations