© 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. 17245
    Prev
    Next
    INDEX
    Explanations

    ser + suffixes

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

    ser followed by ene or endip

    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
     vaginalis
    0.40
     Santos
    0.38
    ципа
    0.38
    羙
    0.38
    咊
    0.38
    ິດ
    0.37
    __|
    0.37
    ઇ
    0.37
    폄
    0.37
    भूमि
    0.37
    POSITIVE LOGITS
    vice
    0.64
    endip
    0.63
     vice
    0.63
    VICE
    0.58
    enade
    0.57
    enity
    0.57
    pentine
    0.56
    VICES
    0.55
     VICE
    0.54
    curities
    0.53
    Activations Density 0.011%

    No Known Activations