© 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. 476
    Prev
    Next
    INDEX
    Explanations

    at Google

    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
    eren
    2.21
    ".$
    1.92
    den
    1.92
    ့
    1.84
    ެ
    1.79
     kaise
    1.78
    ein
    1.77
    ت
    1.70
    cient
    1.69
    eur
    1.68
    POSITIVE LOGITS
    
    2.20
    ಲ್ಲಿ
    2.14
    ঙ্কে
    2.14
    徉
    2.14
    𝕊
    2.13
     superficie
    2.07
     least
    2.03
    रथ
    2.00
    WriteLine
    1.98
    Iddict
    1.98
    Activations Density 0.573%

    No Known Activations