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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 7586
    Prev
    Next
    INDEX
    Explanations

    torch and related words

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

    pytorch program

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    addam
    0.47
     broker
    0.45
     Broker
    0.44
    肋
    0.43
     बकरी
    0.41
     Theoretical
    0.40
     జమ
    0.40
     অধর
    0.40
    物を
    0.40
     هولندا
    0.40
    POSITIVE LOGITS
     torch
    3.34
    torch
    3.06
     Torch
    2.98
    Torch
    2.81
     torches
    2.75
    pytorch
    1.83
     torchvision
    1.69
    횃
    1.53
     TOR
    1.48
    炬
    1.42
    Activations Density 0.009%

    No Known Activations