© 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. 98630
    Prev
    Next
    INDEX
    Explanations

    APPEALS FOR THE CIRCUIT

    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
     docteur
    -0.94
    昆布
    -0.85
     elever
    -0.85
    нем
    -0.84
    روزی
    -0.82
    Dutch
    -0.77
     doorway
    -0.76
     tromper
    -0.75
     contraire
    -0.75
     méda
    -0.75
    POSITIVE LOGITS
    work
    0.77
     jammer
    0.75
    Compose
    0.73
     and
    0.72
    ogyn
    0.72
     depra
    0.70
    azzo
    0.70
     ceil
    0.70
     characteristic
    0.69
     centroid
    0.69
    Activations Density 0.002%

    No Known Activations