© 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. 182914
    Prev
    Next
    INDEX
    Explanations

    tuning adjustments, without drugs

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

    historical and societal concepts

    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
     drank
    0.44
     annealed
    0.43
     anharmonic
    0.42
     arbitr
    0.42
    দুর
    0.42
    。
    0.42
     fórmulas
    0.41
    謂
    0.41
     creases
    0.41
     inviscid
    0.41
    POSITIVE LOGITS
    éroport
    0.52
     जनसंख्या
    0.46
     Arrivals
    0.45
     अलग
    0.43
     přímo
    0.43
     તમારી
    0.43
     सुख
    0.42
     सरकार
    0.42
     đây
    0.42
     वेस्ट
    0.42
    Activations Density 0.002%

    No Known Activations