© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 128958
    Prev
    Next
    INDEX
    Explanations

    explicitly, variables, options, relative

    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
     h
    0.46
    ans
    0.46
    ilesh
    0.46
     k
    0.46
    hes
    0.45
     nette
    0.44
     bothering
    0.42
    urai
    0.42
    iges
    0.41
    et
    0.41
    POSITIVE LOGITS
    変数
    0.52
    ссия
    0.48
    ｹ
    0.48
     צריך
    0.47
    薬
    0.47
    Ⲉ
    0.46
     σημ
    0.46
    としての
    0.45
    ⓶
    0.45
    𝑉
    0.44
    Activations Density 0.006%

    No Known Activations