© 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. 107819
    Prev
    Next
    INDEX
    Explanations

    numbers and citations

    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
    aksikan
    -0.79
    INATION
    -0.75
     Odd
    -0.74
    Lever
    -0.73
     Пра
    -0.73
    йн
    -0.73
    verdi
    -0.73
     Bek
    -0.70
    ött
    -0.70
     Ham
    -0.70
    POSITIVE LOGITS
     ew
    0.74
     außen
    0.73
     lar
    0.71
     μυ
    0.71
     long
    0.71
     dlou
    0.70
     speziellen
    0.69
     gidi
    0.68
    Hippo
    0.68
    SP
    0.68
    Activations Density 0.010%

    No Known Activations