© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-65K
    7. 2087
    Prev
    Next
    INDEX
    Explanations

    expect range claims

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_65k_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
     ف
    1.13
     من
    1.07
     تن
    1.07
     нужно
    1.06
     ILLUSTR
    1.04
     ين
    1.04
     प्रेरणात्मक
    1.03
     recirc
    1.03
     في
    1.03
     التي
    1.02
    POSITIVE LOGITS
     et
    0.77
    staaten
    0.67
     e
    0.66
     states
    0.65
     key
    0.63
     claims
    0.63
    、
    0.63
     partners
    0.61
     و
    0.61
    ・
    0.61
    Activations Density 0.000%

    No Known Activations