© 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-262K
    7. 54471
    Prev
    Next
    INDEX
    Explanations

    material adjectives and qualifiers

    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
    𝐿
    0.45
     Iterator
    0.45
    ጨማሪ
    0.44
     Existing
    0.43
     vibrates
    0.43
     Reds
    0.43
    णिज्य
    0.43
    暠
    0.43
    ມ
    0.43
    =`
    0.42
    POSITIVE LOGITS
    tour
    0.55
     tập
    0.46
     hàng
    0.44
    at
    0.44
     conscience
    0.42
     পোশাক
    0.42
     rembour
    0.42
     ving
    0.41
     amistad
    0.41
    多い
    0.41
    Activations Density 0.002%

    No Known Activations