© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-65K
    7. 6206
    Prev
    Next
    INDEX
    Explanations

    4 8

    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
    greedy
    1.02
    াকৃতিক
    0.86
    contentInset
    0.86
    keszt
    0.82
    کم
    0.80
    蒜
    0.80
    递归
    0.79
    र्य
    0.79
     definidas
    0.79
    Married
    0.79
    POSITIVE LOGITS
    धाम
    0.89
     quadrants
    0.87
     watching
    0.86
     û
    0.84
     pedestal
    0.80
     watch
    0.77
     breath
    0.76
     life
    0.75
     medically
    0.74
     uw
    0.74
    Activations Density 0.009%

    No Known Activations