© 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. 5853
    Prev
    Next
    INDEX
    Explanations

    clauses following punctuation

    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
    $，
    0.24
     shrubs
    0.24
     utilisons
    0.23
     жок
    0.23
     använder
    0.22
     دیکھیں
    0.22
     utilisez
    0.22
     utilisent
    0.22
    ，
    0.22
    ،
    0.22
    POSITIVE LOGITS
    regardless
    0.25
    '.
    0.25
    despite
    0.24
    thus
    0.24
    这也是
    0.23
    oni
    0.22
    hence
    0.22
     despite
    0.22
    tt
    0.21
    yet
    0.21
    Activations Density 0.903%

    No Known Activations