© 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. 67379
    Prev
    Next
    INDEX
    Explanations

    half of, half a, half-life

    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
     informé
    -1.66
    IZACIÓN
    -1.65
     sesiones
    -1.61
     noté
    -1.54
     connue
    -1.54
     lancé
    -1.52
     Comunicación
    -1.52
     terminé
    -1.52
     Then
    -1.52
     brutality
    -1.51
    POSITIVE LOGITS
    ),
    1.84
    .\\
    1.46
    可以说是
    1.44
    以上です
    1.43
    也算是
    1.42
     For
    1.40
    この辺
    1.39
     sach
    1.37
    which
    1.34
    能让
    1.34
    Activations Density 0.003%

    No Known Activations