© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 7824
    Prev
    Next
    INDEX
    Explanations

    18th century elegance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    తుందని
    0.66
     coseno
    0.66
     CLIENTI
    0.64
     UNNEEDED
    0.63
    GONDOR
    0.63
    ᙱ
    0.62
    𐰚
    0.62
     الجذر
    0.62
    枓
    0.61
     implementación
    0.61
    POSITIVE LOGITS
    ſ
    0.80
     ſ
    0.79
    ∣
    0.75
     eſ
    0.72
     〈
    0.69
     approbation
    0.66
     employed
    0.65
     præ
    0.64
     agreeable
    0.64
    d
    0.63
    Activations Density 0.006%

    No Known Activations