© 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. 84115
    Prev
    Next
    INDEX
    Explanations

    sun and solar concepts

    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
    𐬹
    -1.67
    𝟬
    -1.63
    PerformLayout
    -1.60
    -------------</
    -1.59
    และ
    -1.58
     della
    -1.52
    pentru
    -1.46
     of
    -1.46
    __":
    -1.45
    ]+"
    -1.41
    POSITIVE LOGITS
     providing
    1.98
     any
    1.80
    ing
    1.66
     allowing
    1.65
     substantially
    1.55
     Providing
    1.48
     which
    1.48
     provide
    1.46
     facilitating
    1.44
     one
    1.41
    Activations Density 0.019%

    No Known Activations