© 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-16K
    7. 446
    Prev
    Next
    INDEX
    Explanations

    qualifications or conditions

    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_16k_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
    :...
    0.21
    ：
    0.21
     باید
    0.21
     pięk
    0.20
     فقال
    0.19
     ...)
    0.19
    _
    0.19
     zrobi
    0.19
     :");
    0.18
     jaki
    0.18
    POSITIVE LOGITS
     despite
    0.32
     unless
    0.32
    despite
    0.29
     due
    0.28
    unless
    0.27
    although
    0.27
     regardless
    0.26
     although
    0.26
     debido
    0.26
     meskipun
    0.26
    Activations Density 5.393%

    No Known Activations