© 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. 241200
    Prev
    Next
    INDEX
    Explanations

    avoid false balance

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Plastics
    0.53
     Toxicity
    0.50
     Inhibition
    0.50
    匼
    0.49
     MyBatis
    0.49
    FlashValue
    0.48
     Polymers
    0.48
     Enrichment
    0.47
    +\|\
    0.47
     Oppen
    0.47
    POSITIVE LOGITS
    feel
    0.52
    dracht
    0.50
    jog
    0.50
     propietarios
    0.49
     ceas
    0.46
     propriétaires
    0.46
    ª
    0.45
    be
    0.45
    Cri
    0.45
    tive
    0.45
    Activations Density 0.000%

    No Known Activations