© 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. 49839
    Prev
    Next
    INDEX
    Explanations

    angios, angioma, anglian

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

    words or names containing "ang" syllables.

    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_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
    Bum
    -0.93
    interess
    -0.90
    válasz
    -0.86
     Dünya
    -0.86
    Israël
    -0.81
     irgendwo
    -0.81
    molly
    -0.78
    日は
    -0.78
    Interess
    -0.77
     Somewhat
    -0.75
    POSITIVE LOGITS
    ค์
    1.18
    eling
    0.99
    ip
    0.95
    ide
    0.95
    sten
    0.94
    elo
    0.93
    tas
    0.93
    gg
    0.88
    ់
    0.87
    else
    0.85
    Activations Density 0.062%

    No Known Activations