© 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. 7357
    Prev
    Next
    INDEX
    Explanations

    too

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

    too much

    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
     همچ
    0.37
    ᖓ
    0.35
    ̯
    0.34
    ികളെ
    0.33
     আপনা
    0.33
     சிற
    0.32
    ফুদ্দিন
    0.32
     همچنین
    0.32
     ইতি
    0.32
     მონ
    0.32
    POSITIVE LOGITS
     too
    4.94
    too
    4.63
     TOO
    4.50
    Too
    4.41
     Too
    4.31
     слишком
    4.22
    太
    4.06
     terlalu
    4.03
     demasiado
    3.88
    TOO
    3.86
    Activations Density 0.584%

    No Known Activations