© 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-16K
    7. 1081
    Prev
    Next
    INDEX
    Explanations

    come up with

    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
    PIL
    0.93
    }})^{
    0.93
    на
    0.91
    पना
    0.90
     trasero
    0.89
    กิน
    0.88
     کافی
    0.87
    Wer
    0.86
    sam
    0.85
    हे
    0.85
    POSITIVE LOGITS
     létre
    1.42
    ตรฐาน
    1.33
    袭
    1.22
    upp
    1.18
     Heraus
    1.11
     alive
    1.10
    unications
    1.07
     réglementation
    1.07
     politique
    1.07
    不及
    1.07
    Activations Density 0.096%

    No Known Activations