© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 73630
    Prev
    Next
    INDEX
    Explanations

    export class filenames with timestamps

    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
    rvore
    -0.72
    attendre
    -0.70
    變化
    -0.70
     傳
    -0.70
     findOne
    -0.69
    numsp
    -0.69
    bangunan
    -0.69
     考
    -0.69
     uchun
    -0.68
     đựng
    -0.67
    POSITIVE LOGITS
     XIII
    0.88
     impunity
    0.83
     XIV
    0.78
    ルダー
    0.76
    orphan
    0.76
     nå
    0.75
     Stri
    0.75
    alties
    0.72
    NIS
    0.71
     metaphors
    0.70
    Activations Density 0.065%

    No Known Activations