© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 3547
    Prev
    Next
    INDEX
    Explanations

    capital, cape, cap-starts

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

    capital or cap

    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
     కలిసి
    0.39
    드
    0.39
     만
    0.39
     급
    0.38
    調べ
    0.38
     Гали
    0.38
     aplicativos
    0.37
     موسی
    0.37
     cambió
    0.37
    삽
    0.37
    POSITIVE LOGITS
    uccino
    0.71
    ricorn
    0.67
    Cap
    0.65
    itals
    0.64
    istrano
    0.62
    ital
    0.61
    italization
    0.59
    itol
    0.59
    itul
    0.58
    cap
    0.58
    Activations Density 0.074%

    No Known Activations