Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8730
    Prev
    Next
    INDEX
    Explanations

    Achilles tendon and heel support

    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
     органі
    -0.86
     Chry
    -0.82
     Laj
    -0.78
    鏢
    -0.77
     Schrö
    -0.77
    غه
    -0.76
    pause
    -0.75
     краще
    -0.74
    êtement
    -0.72
    Pregunta
    -0.71
    POSITIVE LOGITS
     heels
    5.06
     heel
    2.83
     Heels
    2.53
     heals
    2.52
     Heel
    1.97
    heel
    1.93
    Heel
    1.84
     heal
    1.81
     tails
    1.62
     footsteps
    1.48
    Activations Density 0.032%

    No Known Activations