© 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. 85881
    Prev
    Next
    INDEX
    Explanations

    papers and documents

    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
     wilden
    -1.56
     Fácil
    -1.43
     Garantía
    -1.42
    筈
    -1.41
     The
    -1.41
     harten
    -1.40
     neuen
    -1.39
     terão
    -1.38
    middag
    -1.38
     жена
    -1.38
    POSITIVE LOGITS
    )))))
    1.34
     })
    1.23
     altres
    1.20
    "+
    1.17
    positorio
    1.15
     it
    1.14
    GORITH
    1.14
    گاب
    1.11
    ))))))))
    1.10
    ida
    1.09
    Activations Density 0.058%

    No Known Activations