© 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. 6967
    Prev
    Next
    INDEX
    Explanations

    Gates names and locations

    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
     temen
    -0.75
     ši
    -0.74
     Kein
    -0.73
     secar
    -0.73
     akrab
    -0.71
    Manfaat
    -0.70
     Polsek
    -0.70
     angol
    -0.69
    Steph
    -0.69
    Acetone
    -0.68
    POSITIVE LOGITS
     thou
    0.90
    Gateway
    0.88
    ierr
    0.81
    bmatrix
    0.79
    Gate
    0.77
    mello
    0.76
    пат
    0.76
    mbad
    0.75
    الق
    0.75
    renos
    0.75
    Activations Density 0.009%

    No Known Activations