© 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. 14299
    Prev
    Next
    INDEX
    Explanations

    cyber attacks and warfare

    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
    isan
    2.95
    itura
    2.78
    ichter
    2.70
    作る
    2.70
    급
    2.68
    projectlombok
    2.63
    ጩ
    2.61
    édié
    2.60
    ječ
    2.58
    泊
    2.57
    POSITIVE LOGITS
    netic
    3.19
    s
    3.18
    t
    2.92
    k
    2.72
    dyn
    2.68
    kada
    2.64
    ToWrite
    2.64
    tki
    2.63
    kere
    2.62
    l
    2.61
    Activations Density 0.010%

    No Known Activations