© 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. 12815
    Prev
    Next
    INDEX
    Explanations

    removing or simplifying things

    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
    }
    -2.41
     their
    -2.02
     and
    -1.98
    *
    -1.90
    ’’
    -1.88
     all
    -1.84
     any
    -1.80
     both
    -1.78
     numerous
    -1.76
    ”
    -1.70
    POSITIVE LOGITS
    なんですね
    1.91
    МЫ
    1.80
     Estos
    1.70
     ་
    1.61
     decidedly
    1.58
     Diputados
    1.56
     häufigsten
    1.56
     exercício
    1.56
     asesor
    1.54
     새로운
    1.54
    Activations Density 0.021%

    No Known Activations