© 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. 20996
    Prev
    Next
    INDEX
    Explanations

    listing items

    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
     visibilidad
    -1.53
     suministros
    -1.52
     москва
    -1.38
     traducir
    -1.37
     avancer
    -1.33
     timmar
    -1.31
     gestionar
    -1.30
     kılıf
    -1.28
     transparencia
    -1.28
    ㄩ
    -1.27
    POSITIVE LOGITS
    \\
    1.86
    .\\
    1.54
     \
    1.52
    .\
    1.45
    اء
    1.39
    -\
    1.39
    •
    1.38
     THE
    1.38
    -.
    1.37
     TokenType
    1.37
    Activations Density 0.080%

    No Known Activations