© 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. 9-GEMMASCOPE-2-RES-262K
    7. 8998
    Prev
    Next
    INDEX
    Explanations

    a few followed by common nouns

    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_9_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
    Д
    2.21
    隰
    2.09
    eau
    2.07
    ک
    2.01
     большинство
    1.99
    ेड
    1.97
     clock
    1.93
    al
    1.93
     dich
    1.92
     serem
    1.89
    POSITIVE LOGITS
     dozen
    4.24
     hundred
    3.49
     thousand
    3.09
    dozen
    3.02
    thousand
    2.81
    te
    2.58
    Hundred
    2.58
     actinides
    2.57
    몇
    2.54
    жды
    2.54
    Activations Density 0.167%

    No Known Activations