© 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. 7611
    Prev
    Next
    INDEX
    Explanations

    toe or toes

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

    toes

    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
    ushan
    0.38
    ຊ
    0.37
    ಡಿದ
    0.37
    ඪ
    0.37
    󠁳
    0.37
     norsk
    0.36
     মুসল
    0.36
    OSS
    0.36
    ಾರು
    0.36
    annia
    0.36
    POSITIVE LOGITS
     toe
    3.44
     Toe
    3.16
     toes
    3.03
    Toe
    3.00
    toe
    2.92
     TOE
    2.48
    趾
    1.66
     toen
    1.63
     Toen
    1.52
    oe
    1.23
    Activations Density 0.043%

    No Known Activations