© 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. 7160
    Prev
    Next
    INDEX
    Explanations

    give me a

    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
    i
    -2.31
    e
    -2.28
    on
    -2.13
     these
    -2.08
    夀
    -2.06
    1
    -2.03
    睒
    -1.82
     godk
    -1.81
     =
    -1.80
    3
    -1.80
    POSITIVE LOGITS
    鲎
    2.00
     has
    1.87
    slavery
    1.85
    blooming
    1.76
    sufficiency
    1.72
    迄
    1.70
    感じる
    1.69
     estatu
    1.66
     возможность
    1.64
    décoration
    1.64
    Activations Density 0.052%

    No Known Activations