© 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-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 4851
    Prev
    Next
    INDEX
    Explanations

    flour, powder, spore, Bouba

    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
     Remo
    0.41
    钲
    0.40
     coarser
    0.39
    ремен
    0.38
     cheaply
    0.38
     coastal
    0.37
    тных
    0.37
    ాలా
    0.37
     뉴스
    0.37
    Datas
    0.37
    POSITIVE LOGITS
     rupani
    0.46
     yǔ
    0.46
    wür
    0.42
     hoog
    0.40
    형
    0.40
     Süden
    0.40
     yǐ
    0.38
     discíp
    0.38
    hl
    0.38
     hag
    0.38
    Activations Density 0.046%

    No Known Activations