© 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. 217975
    Prev
    Next
    INDEX
    Explanations

    expense, conducting, download, travail

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

    informed * before, acknowledging injustices

    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
     Presiden
    0.47
     víz
    0.47
     đông
    0.47
     Presidente
    0.46
    日期
    0.46
     baratos
    0.44
    д
    0.44
    充足
    0.44
    肽
    0.44
     presiden
    0.44
    POSITIVE LOGITS
     THROUGH
    0.46
    ARCHITECTURE
    0.44
    FormParams
    0.44
    STRUCTION
    0.43
     AFTER
    0.43
    Opera
    0.43
    CHANGED
    0.43
     החד
    0.43
    newToken
    0.42
    InstanceManager
    0.42
    Activations Density 0.001%

    No Known Activations