© 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. 16-GEMMASCOPE-2-RES-262K
    7. 19871
    Prev
    Next
    INDEX
    Explanations

    country names

    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_16_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
    ON
    0.49
    ’
    0.46
     I
    0.41
     Houses
    0.41
    OCKS
    0.38
    il
    0.38
    em
    0.37
    是被
    0.37
     $\
    0.37
     foreclose
    0.36
    POSITIVE LOGITS
     científ
    0.39
    ként
    0.39
     algebras
    0.39
     राशिफल
    0.39
    ку
    0.38
    kec
    0.38
    keto
    0.38
     полный
    0.38
     bioquímica
    0.37
    vur
    0.37
    Activations Density 0.012%

    No Known Activations