© 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. 54013
    Prev
    Next
    INDEX
    Explanations

    tend tendrils tendinitis tendon

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

    words that begin with "tend" or related to tendons.

    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
     Roca
    -0.81
    chance
    -0.81
    sentence
    -0.69
     Bogotá
    -0.69
     долла
    -0.66
     sb
    -0.66
     Stat
    -0.66
    dean
    -0.66
    Santos
    -0.65
     Minh
    -0.65
    POSITIVE LOGITS
    entious
    0.91
    ausea
    0.89
    ペル
    0.87
    Tend
    0.82
     Nez
    0.81
     TEND
    0.76
     Neuen
    0.75
    رارة
    0.75
     tend
    0.74
     Tenden
    0.73
    Activations Density 0.020%

    No Known Activations