© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-262K
    7. 145830
    Prev
    Next
    INDEX
    Explanations

    open-weights model

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     road
    0.70
     fémin
    0.70
    ᄅ
    0.67
    牵
    0.61
    讽
    0.61
    zieć
    0.61
    ลักษณ์
    0.61
    𓇼
    0.60
     kreat
    0.60
    মণ্ড
    0.60
    POSITIVE LOGITS
     डिल
    0.76
    Deliver
    0.68
     Deployment
    0.68
     Lieferung
    0.67
     Delivery
    0.65
     Voraus
    0.63
     डील
    0.63
     Livraison
    0.62
     Deliver
    0.62
    背景
    0.62
    Activations Density 0.006%

    No Known Activations