© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 71007
    Prev
    Next
    INDEX
    Explanations

    absolute positioning and units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
    త
    0.45
    <0xAD>
    0.43
     actes
    0.41
    企業
    0.40
    社会
    0.40
    pubmed
    0.40
     fragments
    0.39
    ṭ
    0.39
    output
    0.39
     preservatives
    0.39
    POSITIVE LOGITS
     પરંતુ
    0.54
     بغیر
    0.53
     stadion
    0.48
     frustration
    0.47
     फ्रैक्शन
    0.46
     kurze
    0.46
     Cependant
    0.46
     Obtain
    0.45
     Stadion
    0.45
     кожен
    0.45
    Activations Density 0.007%

    No Known Activations