© 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. 98197
    Prev
    Next
    INDEX
    Explanations

    Assessment Appeals

    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
     habari
    -0.74
    Ninja
    -0.73
     Phoenix
    -0.71
    lul
    -0.67
    taal
    -0.66
    uxx
    -0.66
    逮捕
    -0.66
     Моло
    -0.65
    Gris
    -0.65
    ואר
    -0.65
    POSITIVE LOGITS
     landscape
    0.88
     Developer
    0.87
     Mello
    0.85
     parcels
    0.84
     zeichnet
    0.83
     landowner
    0.82
     бай
    0.81
     developer
    0.81
     cores
    0.78
    нодоро
    0.77
    Activations Density 0.006%

    No Known Activations