© 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-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 2920
    Prev
    Next
    INDEX
    Explanations

    asking clarifying questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_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
    Ř
    1.03
    řeb
    1.01
    ně
    0.91
    Ě
    0.90
     ji
    0.88
    Př
    0.87
    álně
    0.86
    ů
    0.85
    ře
    0.85
    mě
    0.84
    POSITIVE LOGITS
     veľ
    1.56
     ďal
    1.56
     alebo
    1.51
    ajú
    1.43
     všet
    1.43
     rých
    1.42
     zariaden
    1.42
     niekoľ
    1.41
     všetky
    1.40
     spoloč
    1.39
    Activations Density 0.016%

    No Known Activations