© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 13990
    Prev
    Next
    INDEX
    Explanations

    when + situations and questions

    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_262k_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
     paradigms
    0.75
     paradigm
    0.67
    they
    0.66
     они
    0.66
    ものです
    0.65
     আবারো
    0.64
    ।
    0.63
    ầm
    0.63
    那些
    0.63
    '.
    0.62
    POSITIVE LOGITS
     analyzing
    1.02
     evaluating
    1.00
    Did
    0.98
    ন্দ
    0.97
     did
    0.93
     investigating
    0.92
     searching
    0.91
     sketching
    0.90
     Did
    0.89
    寯
    0.88
    Activations Density 0.007%

    No Known Activations