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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 14601
    Prev
    Next
    INDEX
    Explanations

    here in, police report, offline maps

    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
    3.39
    います
    3.20
    ों
    3.12
    了
    3.00
    nal
    2.84
    ra
    2.82
    ной
    2.82
    st
    2.68
    ный
    2.61
    ness
    2.59
    POSITIVE LOGITS
    ी
    2.24
    ἲ
    2.03
    pek
    1.96
    ὐ
    1.94
    a
    1.92
    쓰
    1.92
    ٔ
    1.89
    รีย
    1.88
    ibirsk
    1.87
    achtree
    1.86
    Activations Density 0.009%

    No Known Activations