© 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. 7-GEMMASCOPE-2-RES-16K
    7. 3284
    Prev
    Next
    INDEX
    Explanations

    garlic powder, Phantom, double or, AS OS, false or

    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
    nellement
    2.78
    nel
    2.58
    noj
    2.52
     
    2.49
    ン
    2.48
    ร้าง
    2.46
    ned
    2.46
    वटी
    2.41
    rases
    2.41
    ni
    2.35
    POSITIVE LOGITS
    ƅ
    2.69
    կ
    2.63
     chute
    2.50
    =".
    2.50
    ্বের
    2.45
    leaflet
    2.43
    뭉
    2.40
    łożyć
    2.40
    स्टाइल
    2.40
    inalis
    2.32
    Activations Density 0.305%

    No Known Activations