© 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. 14071
    Prev
    Next
    INDEX
    Explanations

    proof of theorems in texts

    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
    ي
    3.75
    s
    3.28
    ی
    3.20
    ים
    3.06
    ्त
    2.84
    ्
    2.83
    يّ
    2.76
    یە
    2.65
    ات
    2.64
    ル
    2.62
    POSITIVE LOGITS
    蜍
    2.81
    ្នាក់
    2.61
    ালী
    2.59
     hs
    2.40
    mn
    2.32
    aceutical
    2.29
    殑
    2.29
    న
    2.23
    meg
    2.22
    msub
    2.22
    Activations Density 0.000%

    No Known Activations