© 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. 22-GEMMASCOPE-2-RES-16K
    7. 2682
    Prev
    Next
    INDEX
    Explanations

    choosing the most proper option

    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_22_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
     '
    1.01
    ↵↵
    0.92
    ↵
    0.91
     "
    0.85
     -
    0.84
     an
    0.82
     *
    0.81
    0.80
     /
    0.80
     a
    0.80
    POSITIVE LOGITS
    
    1.63
    〞
    1.59
     evidences
    1.42
    ㏄
    1.38
     drawed
    1.35
    Ⅶ
    1.35
    
    1.33
     ＜
    1.28
    Ⅳ
    1.28
     equipments
    1.27
    Activations Density 0.118%

    No Known Activations