© 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. 4949
    Prev
    Next
    INDEX
    Explanations

    knowing in multiple languages

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

    expressions of knowing

    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
    aughey
    0.41
     Corbett
    0.37
     Ova
    0.36
     vời
    0.36
     Rx
    0.35
     rx
    0.35
    뜩
    0.35
    放出
    0.34
     Chao
    0.34
     ova
    0.34
    POSITIVE LOGITS
     knew
    0.61
     знали
    0.48
     sabia
    0.47
     знал
    0.45
    ቧ
    0.42
     cheating
    0.41
    greens
    0.41
     известен
    0.41
     Picking
    0.40
     Strings
    0.39
    Activations Density 0.000%

    No Known Activations