© 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. 22-GEMMASCOPE-RES-131K
    7. 129251
    Prev
    Next
    INDEX
    Explanations

    little or few

    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_22/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
    Также
    -2.30
    และ
    -1.88
    がありますが
    -1.87
    それにしても
    -1.83
    План
    -1.81
    somewhat
    -1.81
     oeil
    -1.78
     asfalto
    -1.75
    Напомним
    -1.74
    個人的には
    -1.73
    POSITIVE LOGITS
    ’
    2.75
    t
    2.20
    et
    2.00
    \
    1.85
    It
    1.84
     If
    1.82
    P
    1.74
    太多
    1.70
    c
    1.69
     }
    1.68
    Activations Density 0.023%

    No Known Activations