© 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. 34-GEMMASCOPE-RES-131K
    7. 33725
    Prev
    Next
    INDEX
    Explanations

    første man, Mitt Romney, fullt fungerande, dikt

    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_34/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
     часть
    -0.77
     bénéficient
    -0.75
    parker
    -0.73
    zone
    -0.72
     capabilities
    -0.71
     wersji
    -0.71
     drie
    -0.69
    你不要
    -0.68
    tism
    -0.68
     които
    -0.68
    POSITIVE LOGITS
     tinted
    0.91
     Temperance
    0.86
    Nhi
    0.82
    decke
    0.79
    ographique
    0.77
    Unternehmen
    0.75
    你好
    0.74
    codehaus
    0.74
    Capítulo
    0.73
    霞
    0.73
    Activations Density 0.010%

    No Known Activations