© 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. 10798
    Prev
    Next
    INDEX
    Explanations

    cv2.rectangle(

    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
    禟
    2.55
     igreja
    2.43
     puertas
    2.40
    !\!\
    2.34
    ्वेस्ट
    2.30
     petición
    2.27
     estrutura
    2.26
     quantidade
    2.25
     instituição
    2.24
     автоматтары
    2.19
    POSITIVE LOGITS
    ️
    2.61
     am
    2.17
     کش
    2.08
     hoá
    1.98
     st
    1.85
     dor
    1.85
    تس
    1.83
     گرد
    1.83
     kem
    1.80
    LL
    1.79
    Activations Density 0.015%

    No Known Activations