© 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. 73205
    Prev
    Next
    INDEX
    Explanations

    expressing certainty or uncertainty

    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
     "
    -2.20
     '
    -2.06
     to
    -2.06
    ]
    -1.90
     hermosos
    -1.82
    
    -1.81
     consulté
    -1.80
    躂
    -1.79
     farklı
    -1.79
     Such
    -1.79
    POSITIVE LOGITS
     rằng
    1.75
     who
    1.70
    or
    1.63
     другие
    1.62
     uncertain
    1.62
    si
    1.60
    ably
    1.60
    確
    1.59
    无疑
    1.59
     that
    1.59
    Activations Density 0.020%

    No Known Activations