© 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. 67749
    Prev
    Next
    INDEX
    Explanations

    specific nouns and technical terms

    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
    S
    -2.98
     ähnliche
    -2.50
    ナの
    -2.30
    洐
    -2.25
    もあって
    -2.19
    仂
    -2.19
    性的
    -2.16
    ENT
    -2.14
    詒
    -2.14
    ”,
    -2.06
    POSITIVE LOGITS
    s
    3.55
                    
    2.48
    _
    2.45
    imshow
    2.42
    灕
    2.33
    -
    2.09
    튿
    2.09
    烀
    2.08
    鹮
    2.08
    [
    2.08
    Activations Density 0.000%

    No Known Activations