© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 16315
    Prev
    Next
    INDEX
    Explanations

    minecraft builds and mechanics

    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_22/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)
    -1.26
     our
    -1.22
    澌
    -1.21
     baada
    -1.20
     \%)$
    -1.19
    жду
    -1.18
     triliun
    -1.18
    idelberg
    -1.17
    كتب
    -1.15
     Perfon
    -1.15
    POSITIVE LOGITS
    üstung
    1.17
     chré
    1.17
    ƽ
    1.17
     живе
    1.16
     ölü
    1.10
    hiana
    1.09
    葺
    1.08
    だそうです
    1.07
     fontes
    1.07
    ﾎ
    1.06
    Activations Density 0.027%

    No Known Activations