© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 14473
    Prev
    Next
    INDEX
    Explanations

    English roots, Foo Fighters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_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
     fragile
    1.73
     inflammatory
    1.63
     chronique
    1.63
    確
    1.59
    டாக
    1.57
    来越
    1.56
     antiseptic
    1.55
     sering
    1.53
    偶尔
    1.52
     dilap
    1.51
    POSITIVE LOGITS
    :
    1.55
    ?:
    1.47
    ﺐ
    1.41
     Bagaimana
    1.35
     How
    1.34
     Step
    1.30
    мак
    1.30
    ugan
    1.29
     Identify
    1.29
    ун
    1.29
    Activations Density 0.113%

    No Known Activations