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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 45536
    Prev
    Next
    INDEX
    Explanations

    our Index results, a loved one, side stones, this year

    np_acts-logits-general · gemini-2.5-flash-lite

    you can

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     insidious
    0.57
     distrust
    0.50
     destru
    0.48
     unsus
    0.48
     civilians
    0.47
    ّا
    0.47
    ة
    0.46
     inz
    0.45
     jib
    0.45
     longe
    0.44
    POSITIVE LOGITS
     প্ল
    0.46
    圣诞
    0.46
    ্যোগ
    0.46
     permettent
    0.44
     συγκεκρι
    0.44
    🔳
    0.43
     Newborn
    0.43
    Rightarrow
    0.42
    acaktır
    0.42
    হইবে
    0.42
    Activations Density 0.000%

    No Known Activations