© 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. 17-GEMMASCOPE-2-RES-16K
    7. 13574
    Prev
    Next
    INDEX
    Explanations

    risk assessment and management

    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_17_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
    ים
    2.81
    cology
    2.78
    en
    2.77
    та
    2.58
    ckpt
    2.51
    ت
    2.38
    a
    2.33
    ,}$
    2.31
    ا
    2.30
    idays
    2.30
    POSITIVE LOGITS
     averse
    2.78
    𝗻
    2.77
    𝗥
    2.54
    ناک
    2.36
    𝗿
    2.28
    
    2.24
    𝗲
    2.24
    ણી
    2.23
     aptitude
    2.23
     puesto
    2.21
    Activations Density 0.116%

    No Known Activations