© 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. 1379
    Prev
    Next
    INDEX
    Explanations

    well established or suited

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

    well-being

    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
     <<
    0.43
    ynchus
    0.41
     యుద్ధ
    0.38
     समेत
    0.38
     сильно
    0.37
     અંગે
    0.36
     लॉगिन
    0.36
     还
    0.36
     أما
    0.35
    च्चय
    0.35
    POSITIVE LOGITS
     versed
    1.00
     behaved
    0.92
    behaved
    0.91
     suited
    0.83
    versed
    0.79
    groomed
    0.76
    established
    0.75
    documented
    0.74
    suited
    0.73
    positioned
    0.73
    Activations Density 0.111%

    No Known Activations