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. 8581
    Prev
    Next
    INDEX
    Explanations

    song titles

    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
     ervan
    -1.02
     אם
    -0.94
     tygod
    -0.93
     ........
    -0.91
     OGSÅ
    -0.85
     ...........
    -0.84
    itve
    -0.84
     wezen
    -0.84
    üğü
    -0.83
    verticalLayout
    -0.82
    POSITIVE LOGITS
     précédent
    0.96
     Pt
    0.96
     reprise
    0.94
    intro
    0.93
    ]=
    0.93
    手順
    0.93
    demo
    0.92
    」
    0.92
    ],
    0.92
    <bos>
    0.90
    Activations Density 0.050%

    No Known Activations