© 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. 13-GEMMASCOPE-2-RES-16K
    7. 6897
    Prev
    Next
    INDEX
    Explanations

    easy to

    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_13_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
    د
    2.53
    𝐨
    2.30
    𝐧
    1.95
    োপুরি
    1.95
    ޯ
    1.94
    ว้
    1.90
    miot
    1.88
     vutto
    1.88
    𝐫
    1.87
    льники
    1.85
    POSITIVE LOGITS
     dàng
    3.03
    ufig
    1.95
     segu
    1.93
    राधिक
    1.77
    ⎟
    1.73
    CG
    1.70
    াক্রমে
    1.63
    สบาย
    1.60
    falls
    1.60
     forget
    1.60
    Activations Density 0.255%

    No Known Activations