© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92666
    Prev
    Next
    INDEX
    Explanations

    azaserine, Azayer, azuki, Azel, Azibo, Aziza

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

    pharmaceutical, chemical, or place names starting with "Az".

    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
     таки
    -0.73
    SZ
    -0.73
     Arie
    -0.72
     היש
    -0.71
    getZ
    -0.69
    🚕
    -0.68
    igem
    -0.68
    ليد
    -0.68
     karakter
    -0.68
    Baseball
    -0.67
    POSITIVE LOGITS
     gebraucht
    0.79
    ęło
    0.78
    Naam
    0.78
    hna
    0.78
    町村
    0.76
    inci
    0.75
    estal
    0.75
    𝕂
    0.74
    opaque
    0.74
    ţii
    0.73
    Activations Density 0.024%

    No Known Activations