© 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-65K
    7. 1878
    Prev
    Next
    INDEX
    Explanations

    A followed by ix or quest

    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_65k_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
    ákat
    0.26
    ్వర
    0.24
     redefine
    0.24
     subdue
    0.24
     recreate
    0.24
    缠
    0.23
     collaborate
    0.23
    尽快
    0.23
     brighten
    0.22
    atthakath
    0.22
    POSITIVE LOGITS
     was
    0.31
    e
    0.27
    0
    0.27
    ui
    0.26
     at
    0.25
     đây
    0.25
    ys
    0.25
     this
    0.25
    .,
    0.25
    uch
    0.25
    Activations Density 0.002%

    No Known Activations