© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 119857
    Prev
    Next
    INDEX
    Explanations

    'got to' + action verb

    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
    \
    -2.44
    1
    -2.13
    end
    -1.96
    _
    -1.95
    >
    -1.79
     not
    -1.75
    ),
    -1.75
    es
    -1.67
     a
    -1.67
    re
    -1.66
    POSITIVE LOGITS
    ㍑
    1.90
     նաև
    1.85
    dobe
    1.84
    也将
    1.69
    jęcie
    1.67
    鑷
    1.66
    pág
    1.63
     牙
    1.63
    ின
    1.61
    łyż
    1.59
    Activations Density 0.014%

    No Known Activations