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. 30
    Prev
    Next
    INDEX
    Explanations

    website or social media information

    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
     our
    -1.17
     in
    -0.97
     naszych
    -0.91
    Our
    -0.91
    plz
    -0.91
     any
    -0.90
     protection
    -0.89
     kuliah
    -0.88
     venit
    -0.88
    ёз
    -0.85
    POSITIVE LOGITS
     Instagram
    1.45
    Website
    1.31
    instagram
    1.31
     instagram
    1.31
    website
    1.30
    INFO
    1.30
    Instagram
    1.29
     INFO
    1.21
     Website
    1.16
    <em>
    1.16
    Activations Density 0.007%

    No Known Activations