© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 6887
    Prev
    Next
    INDEX
    Explanations

    natural language processing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    찮
    0.91
     সম্পদের
    0.89
    くなります
    0.86
     Bub
    0.83
    assed
    0.82
     Stability
    0.82
     मध्य
    0.82
     excuse
    0.81
     బ
    0.81
    くない
    0.80
    POSITIVE LOGITS
     within
    1.03
     brightly
    0.97
     proactively
    0.95
     level
    0.93
    针
    0.91
     proactive
    0.87
    潋
    0.86
    Level
    0.86
     expressly
    0.85
    針
    0.85
    Activations Density 0.077%

    No Known Activations