© 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
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 2146
    Prev
    Next
    INDEX
    Explanations

    negative numbers and symbols

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

    negative and command flags

    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
    াহরণ
    0.39
     হইয়৷
    0.39
    চৈতন্যের
    0.37
    ருங்கள்
    0.37
    জেল
    0.37
     ख़ु
    0.36
     freshmen
    0.36
    NewUrlParser
    0.36
     publicly
    0.35
    কানিক্যাল
    0.35
    POSITIVE LOGITS
     (-
    3.50
    (-
    3.14
     $(-
    3.02
     [-
    2.91
     (−
    2.86
     negative
    2.69
    =-
    2.69
     =-
    2.69
     $-
    2.64
    }(-
    2.64
    Activations Density 0.190%

    No Known Activations