© 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. 86923
    Prev
    Next
    INDEX
    Explanations

    Mueller Russian election probe

    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
    tizens
    -0.79
    Kansas
    -0.79
     hessen
    -0.78
    Utah
    -0.76
    rava
    -0.75
    rifts
    -0.73
    outils
    -0.73
    糯
    -0.71
    pausal
    -0.70
    sscanf
    -0.69
    POSITIVE LOGITS
     Russian
    2.22
     Russia
    2.20
     collusion
    1.74
    Russian
    1.57
     Mueller
    1.54
    ロシア
    1.53
     Russians
    1.50
     Rus
    1.47
    Russia
    1.45
     Rusia
    1.45
    Activations Density 0.032%

    No Known Activations