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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 340
    Prev
    Next
    INDEX
    Explanations

    lovely and lively places

    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_65k_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
    Transportation
    0.44
    Downtown
    0.43
    慎
    0.43
     expedit
    0.42
    尽可能
    0.42
     warrantless
    0.42
    权力
    0.41
     subpoena
    0.40
     ধর্মীয়
    0.40
    重大
    0.39
    POSITIVE LOGITS
     cafés
    0.81
     cafes
    0.80
     café
    0.73
     cafe
    0.71
     lovely
    0.68
     €
    0.67
     promenade
    0.66
     promen
    0.66
     euros
    0.64
     Algarve
    0.64
    Activations Density 0.109%

    No Known Activations