© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 12324
    Prev
    Next
    INDEX
    Explanations

    "Elect Australians," Russian "or," Hebrew

    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
    nya
    2.78
    اً
    2.62
    lines
    2.41
    dirs
    2.33
    loan
    2.30
    dub
    2.25
    Publication
    2.22
    笞
    2.22
     correttamente
    2.17
    seekers
    2.16
    POSITIVE LOGITS
    া
    3.19
    ித்த
    3.19
    고
    3.17
    ه
    3.02
    as
    2.98
    e
    2.95
     \]
    2.87
    a
    2.73
    ть
    2.68
    ה
    2.66
    Activations Density 0.002%

    No Known Activations