© 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. 10-GEMMASCOPE-RES-131K
    7. 14552
    Prev
    Next
    INDEX
    Explanations

    database model definitions

    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
     \&
    -1.95
     $-$
    -1.84
    𖣘
    -1.81
    ⟣
    -1.66
    洋服
    -1.59
     $^{\
    -1.55
     \#
    -1.55
    \&
    -1.53
    殲
    -1.52
     --
    -1.51
    POSITIVE LOGITS
     ausreich
    1.48
    Winner
    1.47
    Cuidado
    1.42
    瑧
    1.41
     tijden
    1.40
     solcher
    1.40
     Мы
    1.38
     außerord
    1.38
    ubahan
    1.36
     sogen
    1.36
    Activations Density 0.001%

    No Known Activations