© 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. 4926
    Prev
    Next
    INDEX
    Explanations

    dealing with trauma or treatment

    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
    ்ப
    2.09
    اٹ
    1.89
    ์
    1.89
    ค์
    1.78
    <footer>
    1.76
    낼
    1.69
    영
    1.66
    갓
    1.65
     bis
    1.64
     iler
    1.62
    POSITIVE LOGITS
    𝘳
    3.09
    Ꭾ
    2.97
    rind
    2.75
     quisquam
    2.64
    reciation
    2.61
    भाल
    2.58
    ાર્થી
    2.57
    ivă
    2.56
     MenuView
    2.55
    apeutic
    2.53
    Activations Density 0.313%

    No Known Activations