© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 66497
    Prev
    Next
    INDEX
    Explanations

    digit ofproportion ofratio ofequation of

    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
     кілька
    -2.14
     делает
    -2.08
     acoged
    -2.06
     exportaciones
    -2.05
     negociaciones
    -1.95
     motocicletas
    -1.92
     licencias
    -1.89
     automóviles
    -1.85
     rebajas
    -1.84
    んだよね
    -1.81
    POSITIVE LOGITS
     of
    9.81
    ของ
    1.98
     של
    1.95
    を
    1.87
    の
    1.77
    が
    1.72
    <bos>
    1.72
     for
    1.63
    で
    1.62
     основ
    1.56
    Activations Density 0.064%

    No Known Activations