© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 7558
    Prev
    Next
    INDEX
    Explanations

    soul and spirit

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

    soul

    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
     টিউ
    0.40
    檳
    0.40
     उद्या
    0.39
    ว้าง
    0.38
    тье
    0.38
     नका
    0.37
     মার্কে
    0.37
    symmetric
    0.36
     સહ
    0.36
     జరిగింది
    0.36
    POSITIVE LOGITS
     soul
    4.69
    soul
    4.25
     Soul
    4.22
    Soul
    4.16
     souls
    3.95
    灵魂
    3.77
    魂
    3.61
     Souls
    3.30
     души
    3.03
     душа
    3.02
    Activations Density 0.087%

    No Known Activations