© 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. 1984
    Prev
    Next
    INDEX
    Explanations

    following conditions or lists

    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
     went
    -0.88
    審
    -0.71
     disease
    -0.69
     рано
    -0.68
    펩
    -0.66
    angsaan
    -0.66
    cover
    -0.65
    审
    -0.65
     remained
    -0.64
     hierdie
    -0.64
    POSITIVE LOGITS
     Serien
    0.79
    ighthouse
    0.71
    тивных
    0.70
    verages
    0.69
    NOVA
    0.69
    BUY
    0.69
     jugos
    0.69
    CLAR
    0.69
    orks
    0.68
     CLAR
    0.68
    Activations Density 0.068%

    No Known Activations