© 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. 123552
    Prev
    Next
    INDEX
    Explanations

    kisses and hugs

    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
    _{
    -2.72
    踯
    -2.63
    ),
    -2.47
    镚
    -2.45
    パスタ
    -2.44
     anbef
    -2.39
    viembre
    -2.30
    お肉
    -2.28
     ferrovia
    -2.27
    食感
    -2.27
    POSITIVE LOGITS
     I
    2.27
     famosas
    2.17
    栳
    2.14
     erila
    2.13
     vieja
    2.11
     he
    2.09
    ?"
    2.08
    xo
    2.06
     viejos
    2.06
     Воло
    2.05
    Activations Density 0.005%

    No Known Activations