© 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. 200788
    Prev
    Next
    INDEX
    Explanations

    timing and duration

    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
     약간
    0.48
    angaroo
    0.45
    僄
    0.44
     доста
    0.43
    eliac
    0.43
     немного
    0.43
    Picklist
    0.43
    
    0.42
     แต่
    0.42
    但是
    0.41
    POSITIVE LOGITS
     activiteiten
    0.47
     voir
    0.46
     activités
    0.45
     Exemple
    0.45
     apprendre
    0.44
     célèbre
    0.44
     températures
    0.44
     partager
    0.43
     attaque
    0.43
     betrachtet
    0.43
    Activations Density 0.003%

    No Known Activations