© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 12065
    Prev
    Next
    INDEX
    Explanations

    what specific aspects to explore

    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
    nika
    1.34
    طان
    1.27
    ্লাহ
    1.26
    絕對
    1.25
     الطبي
    1.21
     برابر
    1.18
     مج
    1.15
     은
    1.15
     기름
    1.14
    わない
    1.13
    POSITIVE LOGITS
     trajets
    1.56
    izedBox
    1.55
     algéb
    1.53
    Shawn
    1.48
    工夫
    1.45
     Trouver
    1.44
    Algo
    1.44
     লেখাপ
    1.43
     mudanças
    1.43
     Surround
    1.43
    Activations Density 0.146%

    No Known Activations