© 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. 1710
    Prev
    Next
    INDEX
    Explanations

    online sites

    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
     
    -2.97
     “
    -2.25
    橚
    -2.16
    F
    -2.13
    D
    -2.13
    A
    -2.09
    it
    -2.08
    あります
    -2.06
    K
    -2.06
    U
    -2.05
    POSITIVE LOGITS
    饪
    2.89
    謦
    2.69
    鬭
    2.69
    锱
    2.42
    筇
    2.33
    艄
    2.31
    躂
    2.20
    呿
    2.19
    ATELY
    2.13
    wiſe
    2.13
    Activations Density 0.017%

    No Known Activations