© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 65942
    Prev
    Next
    INDEX
    Explanations

    aboard a ship

    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
    躄
    -3.03
     approval
    -2.39
    鼴
    -2.31
     appalling
    -2.27
    หรือ
    -2.22
    S
    -2.19
     dotyczące
    -2.17
     {
    -2.17
     bebés
    -2.14
     всем
    -2.13
    POSITIVE LOGITS
    "
    2.73
    ⟝
    2.50
    </i>
    2.48
     carelessly
    2.44
     I
    2.36
     huddled
    2.27
     ridd
    2.17
     fashioned
    2.16
     casually
    2.13
    ON
    2.11
    Activations Density 0.002%

    No Known Activations