© 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. 9958
    Prev
    Next
    INDEX
    Explanations

    comparative conjunctions

    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
     playable
    0.44
     parete
    0.42
     videomuz
    0.41
    ">)</
    0.40
     Ress
    0.40
     roughness
    0.39
     dyeing
    0.39
     формата
    0.38
     aeration
    0.38
     rapporto
    0.38
    POSITIVE LOGITS
    N
    0.46
     لكن
    0.45
     परन्तु
    0.42
     लेकिन
    0.41
     પરંતુ
    0.40
     ប៉ុ
    0.39
     किन्तु
    0.39
     तथा
    0.38
    ERROR
    0.38
    但在
    0.38
    Activations Density 0.000%

    No Known Activations