© 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. 2092
    Prev
    Next
    INDEX
    Explanations

    BDP, Pavers, Eagledale, leryn, Leavenworth, Daikin

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

    creating common compound words

    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
     соору
    0.45
    Missouri
    0.42
    豺
    0.42
    西安
    0.41
    AIRE
    0.39
    )}}\
    0.39
    Literatur
    0.39
     voluminous
    0.39
    佛
    0.39
     traiter
    0.38
    POSITIVE LOGITS
     therefore
    0.51
    inas
    0.47
    gen
    0.46
    bel
    0.46
     Therefore
    0.45
     তাই
    0.45
    Therefore
    0.45
    oseconds
    0.45
    ewidth
    0.43
    genes
    0.43
    Activations Density 0.178%

    No Known Activations