© 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. 60805
    Prev
    Next
    INDEX
    Explanations

    thus far

    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
    t
    -2.50
    ing
    -2.41
    讥
    -2.19
    并未
    -2.14
    ごちそう
    -2.09
    鴟
    -2.08
    気持ちを
    -2.08
    あっという
    -2.06
    俨
    -2.06
    比べて
    -2.05
    POSITIVE LOGITS
    This
    3.00
    \
    2.48
     店
    2.47
    If
    2.34
    ſſel
    2.27
    there
    2.23
    旅程
    2.23
    然而
    2.14
    onsors
    2.14
    <()>
    2.03
    Activations Density 0.001%

    No Known Activations