© 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. 1602
    Prev
    Next
    INDEX
    Explanations

    predicting subsequent words

    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
    訲
    0.81
    洷
    0.79
    䊂
    0.78
    桻
    0.78
    秞
    0.77
    晠
    0.77
    㖣
    0.77
    剻
    0.76
    䇢
    0.76
    㳻
    0.76
    POSITIVE LOGITS
    瞧
    1.08
     shenanigans
    0.94
    moniker
    0.93
     intricacies
    0.92
     prudence
    0.91
     receptacles
    0.90
     prowess
    0.89
     indulgence
    0.89
     delectable
    0.89
     مذکور
    0.86
    Activations Density 5.770%

    No Known Activations