© 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. 226795
    Prev
    Next
    INDEX
    Explanations

    intend to plant

    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
    h
    0.54
    ophore
    0.49
    ani
    0.48
    eme
    0.48
     Th
    0.47
     sound
    0.47
    ih
    0.46
    ajikan
    0.45
    lname
    0.45
    al
    0.45
    POSITIVE LOGITS
     róż
    0.50
    💋
    0.49
     অনুক
    0.48
     druck
    0.48
    Contrary
    0.47
    ≠
    0.47
    𝕆
    0.47
    тою
    0.47
    يو
    0.46
    ґ
    0.45
    Activations Density 0.000%

    No Known Activations