© 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. 7260
    Prev
    Next
    INDEX
    Explanations

    percentages and over

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

    interest rates and APY

    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
    上次
    0.41
    vironment
    0.40
    ாவும்
    0.40
    薰
    0.39
    鵜
    0.39
    atoon
    0.38
    ក្នុងការ
    0.37
     রো
    0.36
     भारती
    0.36
    enfance
    0.36
    POSITIVE LOGITS
     over
    0.65
     über
    0.54
     peste
    0.53
    over
    0.52
     discrete
    0.46
     Over
    0.43
    过
    0.39
     över
    0.39
    oer
    0.39
     ओवर
    0.38
    Activations Density 0.000%

    No Known Activations