© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 116041
    Prev
    Next
    INDEX
    Explanations

    Legion posts and veterans

    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
     tudo
    -0.81
    fendi
    -0.76
    intenant
    -0.75
     aceptar
    -0.74
    áciu
    -0.72
     y
    -0.71
    dflare
    -0.70
    unik
    -0.70
     veinte
    -0.70
     telecom
    -0.69
    POSITIVE LOGITS
     posts
    1.69
     Legion
    1.63
     Posts
    1.56
     legion
    1.55
    Legion
    1.41
    Veterans
    1.41
     POSTS
    1.40
     veterans
    1.34
     Veterans
    1.34
    posts
    1.32
    Activations Density 0.011%

    No Known Activations