© 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. 1641
    Prev
    Next
    INDEX
    Explanations

    earning, gaining, or receiving recognition

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

    quickly gained

    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
     volut
    0.45
    軚
    0.45
     അനുവദ
    0.44
     कोस
    0.43
    諦
    0.43
     =-\
    0.43
     pengurangan
    0.42
     loser
    0.41
    =-\
    0.40
     सूचित
    0.40
    POSITIVE LOGITS
     garner
    1.57
     garnered
    1.46
     earned
    1.34
     завое
    1.29
     earning
    1.25
     zdoby
    1.25
     earns
    1.21
     conquistar
    1.19
    跻
    1.16
     earn
    1.16
    Activations Density 0.435%

    No Known Activations