© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 28535
    Prev
    Next
    INDEX
    Explanations

    classes, activities, groups

    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
    ciato
    0.46
     早
    0.46
    Fres
    0.45
     vroeg
    0.45
    en
    0.45
    cut
    0.45
    Wert
    0.44
    早
    0.43
     stycz
    0.43
    зова
    0.42
    POSITIVE LOGITS
     clubs
    0.58
     verbs
    0.50
     faculties
    0.49
     adjectives
    0.48
     journalism
    0.46
     protagonists
    0.46
     campaigners
    0.45
     sporting
    0.45
     industries
    0.44
     blogging
    0.44
    Activations Density 0.002%

    No Known Activations