© 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. 7987
    Prev
    Next
    INDEX
    Explanations

    political communication, solicitor, consulting, environmental, director

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

    quantization bits

    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
     মাননীয়
    0.57
     می‌باشد
    0.53
    﨑
    0.53
     대하여
    0.53
    하여
    0.52
    விற்கு
    0.52
     মোঃ
    0.50
    臺灣
    0.50
     বাড়ীতে
    0.49
    த்தினை
    0.48
    POSITIVE LOGITS
     reportedly
    0.65
     দেশটির
    0.61
     meski
    0.61
     शख्स
    0.58
     ­
    0.57
     महज
    0.54
     staffers
    0.54
     मुताबिक
    0.52
    कायदा
    0.52
     इलाके
    0.51
    Activations Density 0.167%

    No Known Activations