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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 126
    Prev
    Next
    INDEX
    Explanations

    heritage register listings

    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
    flav
    -0.84
     lietu
    -0.71
     BSEB
    -0.69
    سع
    -0.69
     Peking
    -0.69
     Collateral
    -0.68
    Ệ
    -0.68
    ➪
    -0.68
    Disappear
    -0.68
    hling
    -0.67
    POSITIVE LOGITS
     colectiva
    0.81
     outcomes
    0.80
     DA
    0.80
     coding
    0.79
    ϑ
    0.77
     Strategic
    0.77
     ठ
    0.76
     development
    0.76
     средней
    0.75
     alemanes
    0.75
    Activations Density 0.002%

    No Known Activations