© 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. 11003
    Prev
    Next
    INDEX
    Explanations

    you think you know

    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
    というのは
    2.72
     라는
    2.68
     를
    2.58
    Whilst
    2.48
     Whilst
    2.47
     ちょっと
    2.39
     얘기를
    2.37
     其实
    2.35
     นั้น
    2.34
     אשר
    2.34
    POSITIVE LOGITS
    ș
    1.80
     COVID
    1.75
    ște
    1.69
    șa
    1.57
    Trusted
    1.56
     TikTok
    1.55
    ăș
    1.53
    🫶
    1.52
     ș
    1.52
    țin
    1.49
    Activations Density 0.835%

    No Known Activations