© 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-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 3641
    Prev
    Next
    INDEX
    Explanations

    f followed by "

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-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
     œuvre
    0.86
     ジュ
    0.81
     י
    0.81
     пор
    0.77
     Dong
    0.75
     công
    0.74
     PowerPoint
    0.74
     Myst
    0.73
     গুণে
    0.72
    supers
    0.72
    POSITIVE LOGITS
    "
    0.73
    Allow
    0.70
    Academic
    0.68
     শত্র
    0.67
    Who
    0.67
    leyebilirsiniz
    0.66
    '
    0.65
    nunique
    0.64
    who
    0.63
    椒
    0.63
    Activations Density 0.039%

    No Known Activations