© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 11831
    Prev
    Next
    INDEX
    Explanations

    dialog or window

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

    dialogue flow

    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_40_width_16k_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
     unlocked
    0.44
    CHK
    0.43
     KeyError
    0.43
     કરતા
    0.41
     locked
    0.41
    ᓲ
    0.40
     unlock
    0.40
    ပါ
    0.39
    ഷ്ട
    0.39
    alen
    0.38
    POSITIVE LOGITS
     конец
    0.49
    Beginning
    0.48
    End
    0.44
     представитель
    0.44
     Beginning
    0.43
    ётся
    0.42
    ጩ
    0.39
     ريا
    0.39
     نهايه
    0.39
     beginning
    0.38
    Activations Density 0.012%

    No Known Activations