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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108478
    Prev
    Next
    INDEX
    Explanations

    numerical identifiers and dates

    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
     kostet
    -0.93
    ！(
    -0.92
     Gemeinsame
    -0.91
    espn
    -0.88
     Popis
    -0.85
    饅
    -0.83
    (´
    -0.81
    octubre
    -0.81
    isole
    -0.81
     править
    -0.80
    POSITIVE LOGITS
    pp
    1.02
    ea
    0.99
    zan
    0.93
    ull
    0.91
    ुल
    0.89
    lab
    0.88
     Henne
    0.88
    ali
    0.88
    zu
    0.88
    hara
    0.87
    Activations Density 0.012%

    No Known Activations