© 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. 23675
    Prev
    Next
    INDEX
    Explanations

    technical development programmes

    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
    gya
    -0.95
     estrateg
    -0.92
     biograf
    -0.90
     Kanye
    -0.89
     desinf
    -0.83
     minimalis
    -0.82
     CLI
    -0.82
     маль
    -0.82
     ہم
    -0.82
     kuto
    -0.82
    POSITIVE LOGITS
     desco
    1.16
     trades
    1.04
     heritage
    1.00
     baseline
    1.00
     effort
    0.98
     maturing
    0.94
     matured
    0.94
     maturity
    0.94
     mature
    0.92
     milestones
    0.91
    Activations Density 0.030%

    No Known Activations