© 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. 41332
    Prev
    Next
    INDEX
    Explanations

    RID, Luis, Hundreds, Since, <?

    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
    There
    -2.48
    The
    -2.39
    That
    -2.25
     intricacies
    -2.20
    One
    -2.17
     intricate
    -2.17
     one
    -2.16
     eight
    -2.16
    ᚺ
    -2.14
     three
    -2.13
    POSITIVE LOGITS
    䊐
    2.16
    鯢
    2.11
    耵
    2.06
    鱨
    2.05
     dando
    2.05
     praticamente
    1.96
    sandalia
    1.94
     dieß
    1.92
     immen
    1.92
     ハーフ
    1.91
    Activations Density 0.000%

    No Known Activations