Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 11594
    Prev
    Next
    INDEX
    Explanations

    closing parentheses and brackets

    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
     vutto
    0.42
     zkušen
    0.41
     خواست
    0.40
    นม
    0.40
    $).
    0.39
    MERS
    0.39
    ClFN
    0.38
     wieku
    0.38
     درصد
    0.38
     )।
    0.38
    POSITIVE LOGITS
     chans
    0.49
     my
    0.48
     fun
    0.46
     ll
    0.45
    uga
    0.45
     buddies
    0.45
     we
    0.44
     family
    0.43
     upscale
    0.41
    i
    0.41
    Activations Density 0.014%

    No Known Activations