© 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. 19602
    Prev
    Next
    INDEX
    Explanations

    media and topic labels

    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
    ,
    -1.58
     []:
    -1.56
    ゔ
    -1.32
    atürk
    -1.30
    那时
    -1.28
     \&
    -1.26
     BOTH
    -1.24
    ();
    -1.24
    ⡱
    -1.23
     AGAIN
    -1.19
    POSITIVE LOGITS
     menggunakan
    1.47
     jeho
    1.46
    бина
    1.37
     jego
    1.35
     vsak
    1.28
     use
    1.27
     his
    1.26
    sä
    1.25
     sebagainya
    1.23
     pouco
    1.22
    Activations Density 0.002%

    No Known Activations