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. 7957
    Prev
    Next
    INDEX
    Explanations

    Riemann, Raman, Ricci, mannian concepts

    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
     Ranger
    -0.77
     huile
    -0.75
    Rangers
    -0.73
     권
    -0.73
    uelas
    -0.70
    瘘
    -0.70
     Galerie
    -0.69
    эш
    -0.68
     mahu
    -0.68
    Ranger
    -0.68
    POSITIVE LOGITS
    ANCA
    0.68
     Integration
    0.65
    市の
    0.65
    xl
    0.65
    esi
    0.65
    显
    0.64
     integration
    0.64
     Gold
    0.64
     сро
    0.63
    PAI
    0.63
    Activations Density 0.040%

    No Known Activations