© 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. 84797
    Prev
    Next
    INDEX
    Explanations

    creating or recreating something new

    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
    ди
    0.44
    ens
    0.42
    ization
    0.41
     Folgen
    0.41
     ensued
    0.40
    ے
    0.40
     delineated
    0.39
    ர
    0.39
    ای
    0.39
     Изда
    0.39
    POSITIVE LOGITS
     halibut
    0.45
     alcohol
    0.44
     pickle
    0.43
     ammonium
    0.43
     আজও
    0.43
     lipoprotein
    0.43
     calorie
    0.43
     facelift
    0.43
    醋
    0.42
     paraffin
    0.42
    Activations Density 0.007%

    No Known Activations