© 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. 33091
    Prev
    Next
    INDEX
    Explanations

    aerial photographs

    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
     keep
    -0.81
    endphp
    -0.70
    sys
    -0.69
     analytic
    -0.66
     Play
    -0.66
    紡
    -0.65
     пы
    -0.65
     keeps
    -0.65
    endios
    -0.65
    خل
    -0.63
    POSITIVE LOGITS
    NOSTIC
    0.79
    rsch
    0.73
    Friend
    0.73
     צו
    0.72
    зацию
    0.72
    辋
    0.71
     Imagen
    0.68
     بابا
    0.67
    Frank
    0.67
     concluding
    0.66
    Activations Density 0.052%

    No Known Activations