© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 110933
    Prev
    Next
    INDEX
    Explanations

    certainty and variety

    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
     Stadium
    0.48
    ifi
    0.47
    bar
    0.47
    đ
    0.45
     I
    0.44
    ka
    0.44
    p
    0.43
    pg
    0.43
    il
    0.43
    v
    0.43
    POSITIVE LOGITS
     rougeâtres
    0.51
    존
    0.47
    removeChild
    0.46
     Certaines
    0.46
    زالة
    0.46
    জেলার
    0.46
     classiques
    0.46
    روح
    0.46
    кових
    0.46
    swedish
    0.46
    Activations Density 0.003%

    No Known Activations