© 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. 81811
    Prev
    Next
    INDEX
    Explanations

    remove, select, and control

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

    positive descriptions like "amazing"

    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
    Francesco
    0.48
    ਲ
    0.48
    ट
    0.47
     inconn
    0.45
    很是
    0.45
    าร
    0.44
    ل
    0.44
    ฟ
    0.44
    j
    0.44
    盻
    0.44
    POSITIVE LOGITS
     glaze
    0.45
     gluten
    0.45
     residues
    0.42
     permettra
    0.42
    guides
    0.42
     নিন
    0.42
     contaminants
    0.42
     suscipit
    0.42
     slugs
    0.42
     নিদর্শন
    0.41
    Activations Density 0.001%

    No Known Activations