© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 10044
    Prev
    Next
    INDEX
    Explanations

    find out what

    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
     such
    -1.42
     آذر
    -1.23
    });*/
    -1.22
     kreis
    -1.20
    ungalows
    -1.20
    ⃙
    -1.20
    着自己的
    -1.19
    ſtra
    -1.17
     三角
    -1.17
    않
    -1.15
    POSITIVE LOGITS
     plezier
    1.16
     liefde
    1.14
    他們
    1.12
     mantuvo
    1.11
     cominci
    1.10
     xícara
    1.09
     condividere
    1.09
     trattano
    1.09
     but
    1.08
     indoss
    1.07
    Activations Density 0.037%

    No Known Activations