© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 48503
    Prev
    Next
    INDEX
    Explanations

    lichen, specific terms

    np_acts-logits-general · gemini-2.5-flash-lite

    code or technical document opening elements like curly braces and special characters.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    to
    -2.47
    these
    -2.23
    for
    -2.13
    you
    -1.97
    any
    -1.95
    ႐
    -1.95
    
    -1.92
    which
    -1.89
    いれば
    -1.89
    睺
    -1.88
    POSITIVE LOGITS
     {
    2.19
     identical
    2.02
    rógeno
    1.95
     utilise
    1.90
     differing
    1.87
     nedenle
    1.87
     véritable
    1.85
    iding
    1.84
    時間
    1.82
     совершенно
    1.82
    Activations Density 0.000%

    No Known Activations