Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7839
    Prev
    Next
    INDEX
    Explanations

    semaphore, parapet, hookah, haiku, mnemonic, oracle

    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
     distinctive
    -1.22
     predominantly
    -1.20
    nearly
    -1.15
     pivotal
    -1.15
     ativo
    -1.13
    殍
    -1.13
     финан
    -1.11
     extremely
    -1.09
     exceptionally
    -1.06
    dann
    -1.05
    POSITIVE LOGITS
    {
    1.13
     craze
    1.01
    📢
    1.00
    ский
    0.97
     (
    0.96
     लाख
    0.93
    
    0.93
     ibis
    0.91
    ceous
    0.90
    клей
    0.90
    Activations Density 0.238%

    No Known Activations