© 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. 70473
    Prev
    Next
    INDEX
    Explanations

    names starting with krist

    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
    -3.03
    ться
    -2.98
    на
    -2.44
     Kegiatan
    -2.34
     ailing
    -2.19
     THIS
    -2.19
    il
    -2.19
    龶
    -2.16
     That
    -2.14
     With
    -2.09
    POSITIVE LOGITS
    寕
    2.81
    {
    2.50
    ‘’
    2.45
    釓
    2.39
    o
    2.38
    providedIn
    2.36
    ,’’
    2.28
     ‘‘
    2.28
    ”:
    2.27
    commodation
    2.23
    Activations Density 0.002%

    No Known Activations