© 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. 191
    Prev
    Next
    INDEX
    Explanations

    'Don't' followed by a verb

    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
    inis
    0.80
    ok
    0.79
    uada
    0.66
    u
    0.64
    i
    0.64
    ij
    0.64
    otricha
    0.62
    zy
    0.62
    inu
    0.62
    ini
    0.60
    POSITIVE LOGITS
     HUOBI
    0.94
    Дру
    0.89
    SHARED
    0.89
    Благо
    0.88
    ন
    0.88
    NEGATIVE
    0.87
     стандарт
    0.87
    Subtract
    0.87
    Зна
    0.86
    Typical
    0.86
    Activations Density 1.078%

    No Known Activations