© 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
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 276
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and probability

    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_40_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
    imha
    0.38
    ẫ
    0.37
    𝙪
    0.35
     transparencia
    0.35
    ística
    0.34
    textAlign
    0.34
     texts
    0.33
    Texts
    0.33
    谋
    0.33
     peacefully
    0.33
    POSITIVE LOGITS
    丳
    0.34
    \{
    0.34
    \%
    0.31
     Flächen
    0.30
     Anzahl
    0.29
    啝
    0.29
    \}
    0.28
     Ath
    0.28
     {-
    0.28
    ्थ
    0.28
    Activations Density 0.000%

    No Known Activations