© 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. 68173
    Prev
    Next
    INDEX
    Explanations

    code elements and keywords

    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
     this
    -2.53
     make
    -2.48
     what
    -2.44
     there
    -2.39
     by
    -2.31
     one
    -2.30
     During
    -2.27
     Despite
    -2.16
     get
    -2.09
    Despite
    -2.09
    POSITIVE LOGITS
    嫑
    2.42
    穑
    2.16
    嗩
    2.14
    螣
    2.06
     ネック
    2.02
     ส์
    1.98
    鹩
    1.98
    矬
    1.98
    ,;
    1.98
     vijf
    1.98
    Activations Density 0.025%

    No Known Activations