© 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. 7817
    Prev
    Next
    INDEX
    Explanations

    charming and cute descriptions

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

    charming, wholesome, adorable

    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
    😨
    0.69
    凄い
    0.66
    震撼
    0.66
     horrific
    0.65
     horrifying
    0.64
     impresionante
    0.64
    Powerful
    0.64
    😱
    0.63
    powerful
    0.63
    Dramatic
    0.63
    POSITIVE LOGITS
     charming
    1.63
     cheerful
    1.55
     endearing
    1.46
     cheery
    1.42
     whimsical
    1.41
     lovable
    1.40
     playful
    1.33
     joyful
    1.30
     cheerfully
    1.30
     Charming
    1.30
    Activations Density 0.162%

    No Known Activations