© 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. 12442
    Prev
    Next
    INDEX
    Explanations

    near locations, retyping integer

    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
    了
    3.75
    اً
    3.65
    ्स
    3.60
    ল
    3.56
    lardan
    3.50
    tanto
    3.49
    此之外
    3.48
    ン
    3.46
    ا
    3.38
    ो
    3.37
    POSITIVE LOGITS
    amp
    2.67
    𝙚
    2.35
    ടിച്ചു
    2.33
    issue
    2.28
     reg
    2.23
    uses
    2.23
    attachments
    2.23
    臾
    2.21
    𝙣
    2.21
     rec
    2.21
    Activations Density 0.016%

    No Known Activations