© 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-65K
    7. 8142
    Prev
    Next
    INDEX
    Explanations

    Kunlun Mountains

    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_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
    യിൽ
    0.64
    ნება
    0.58
     Einf
    0.57
    伝
    0.56
     ба
    0.56
     Indien
    0.55
     предназна
    0.55
     pattern
    0.55
     선정
    0.54
     रानी
    0.54
    POSITIVE LOGITS
    ့်
    0.85
    
    0.77
    CCOCC
    0.73
     superimposed
    0.72
     assaulting
    0.70
    ियमित
    0.69
    武器
    0.68
    ᅲ
    0.68
    PAAm
    0.66
    ⴹ
    0.66
    Activations Density 0.612%

    No Known Activations