© 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. 532
    Prev
    Next
    INDEX
    Explanations

    Mississippi

    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
     exploding
    -0.82
    ächtige
    -0.82
     busted
    -0.81
     exploded
    -0.81
     rupture
    -0.79
     burst
    -0.77
     bursting
    -0.77
    pops
    -0.75
     Burst
    -0.74
     rup
    -0.73
    POSITIVE LOGITS
    矛盾
    0.75
    deleteById
    0.72
    江戸
    0.71
    函
    0.70
    िश
    0.70
    กก
    0.68
     democrats
    0.68
     Corral
    0.67
     step
    0.66
     boite
    0.66
    Activations Density 0.014%

    No Known Activations