© 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. 160
    Prev
    Next
    INDEX
    Explanations

    on the

    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
     was
    0.66
    ’
    0.64
    ,
    0.64
     is
    0.63
     has
    0.63
     and
    0.62
     of
    0.59
    iffe
    0.59
     have
    0.59
    ist
    0.59
    POSITIVE LOGITS
    ባድ
    0.70
    сюда
    0.68
    یثیت
    0.64
    ясплат
    0.63
    MEMORY
    0.62
    𝙫
    0.61
    ERCISE
    0.61
    ኩል
    0.60
    𝒏
    0.60
    GetName
    0.60
    Activations Density 2.133%

    No Known Activations