© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1333
    Prev
    Next
    INDEX
    Explanations

    Bitmap create

    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
    Voor
    -0.72
    JOH
    -0.71
     inspir
    -0.69
    ዞ
    -0.68
    verhältnisse
    -0.68
     Voor
    -0.67
     JOH
    -0.67
     Oceanography
    -0.66
     влия
    -0.66
    acuzzi
    -0.66
    POSITIVE LOGITS
     syscall
    0.67
     نع
    0.66
     Dust
    0.66
     Mahan
    0.65
    Dust
    0.65
     junctions
    0.65
     connections
    0.64
     passing
    0.64
     napkins
    0.63
    ftant
    0.63
    Activations Density 0.053%

    No Known Activations