© 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. 4884
    Prev
    Next
    INDEX
    Explanations

    natural logarithm

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

    natural logarithm

    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
    personen
    0.45
    Joey
    0.43
     佐
    0.42
     perímetro
    0.42
     dukkh
    0.41
    佐
    0.41
    kinetic
    0.41
    瀧
    0.41
    qtd
    0.40
    nett
    0.40
    POSITIVE LOGITS
     природ
    0.62
     प्राकृतिक
    0.60
     natural
    0.58
     натура
    0.54
     NATURAL
    0.53
    Natural
    0.52
     자연
    0.52
     naturali
    0.52
     طبیعی
    0.51
     Natural
    0.51
    Activations Density 0.000%

    No Known Activations