© 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. 165076
    Prev
    Next
    INDEX
    Explanations

    Swedish verbs and concepts

    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
    鏄
    0.40
    ={()=>
    0.40
    >\
    0.39
    Lov
    0.39
    getKeyCode
    0.38
    ToBounds
    0.38
    zzles
    0.38
    লো
    0.37
    ට්ට
    0.37
    驴
    0.37
    POSITIVE LOGITS
     café
    0.41
     घड़ी
    0.41
     oy
    0.40
     conditioning
    0.39
    тю
    0.39
    cafe
    0.39
     cafe
    0.39
     resident
    0.38
     Bree
    0.38
     holistic
    0.37
    Activations Density 0.003%

    No Known Activations