© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 92379
    Prev
    Next
    INDEX
    Explanations

    company, students, system, again, makes

    np_acts-logits-general · gemini-2.5-flash-lite

    sexual or harm

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Quaternion
    0.47
    <0x84>
    0.42
     Package
    0.42
     замеча
    0.41
    Old
    0.41
    னித
    0.41
    isle
    0.40
    !-
    0.40
     Pregnant
    0.40
    hou
    0.40
    POSITIVE LOGITS
    ە
    0.47
     را
    0.46
    ﻳ
    0.46
     medya
    0.45
     judiciary
    0.45
    ﻴ
    0.44
     أو
    0.43
    ினி
    0.43
     મી
    0.43
    են
    0.43
    Activations Density 0.000%

    No Known Activations