© 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. 9-GEMMASCOPE-2-RES-16K
    7. 2079
    Prev
    Next
    INDEX
    Explanations

    major cities

    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_9_width_16k_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
    y
    1.63
    radioButton
    1.59
    
    1.55
    yyyyyyyy
    1.50
    distan
    1.48
    ⅜
    1.48
    ления
    1.47
     emitida
    1.44
    f
    1.44
    entlichen
    1.43
    POSITIVE LOGITS
    ि
    1.79
    𝘢
    1.72
    м
    1.63
     chills
    1.62
    ⠀⠀⠀⠀
    1.62
     curb
    1.56
     micelles
    1.56
    िवा
    1.55
    න්
    1.55
     Thirdly
    1.55
    Activations Density 0.085%

    No Known Activations