© 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. 105611
    Prev
    Next
    INDEX
    Explanations

    making easier

    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
     alterations
    -2.42
     disparate
    -2.28
     we
    -2.27
     You
    -2.23
    ༅
    -2.19
     convincing
    -2.14
    ocidade
    -2.11
    醅
    -2.11
    経歴
    -2.09
    ⼭
    -2.06
    POSITIVE LOGITS
    >
    2.70
     одну
    2.58
    さてさて
    2.42
    */
    2.38
    U
    2.36
    苼
    2.34
    0
    2.33
    というわけで
    2.30
    n
    2.27
    ஂ
    2.27
    Activations Density 0.007%

    No Known Activations