© 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. 108124
    Prev
    Next
    INDEX
    Explanations

    warranty of merchantability

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

    freedoms of speech or purpose

    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
    о
    0.49
     включая
    0.48
    ة
    0.48
    aternary
    0.46
     озера
    0.46
    О
    0.46
    ুর
    0.45
    որ
    0.45
    慶
    0.44
    鲈
    0.44
    POSITIVE LOGITS
     landowner
    0.45
     intolerance
    0.44
     dissu
    0.44
     MND
    0.44
     Tregs
    0.43
     criminality
    0.43
     deterrence
    0.43
     मालूम
    0.43
     criminal
    0.42
     judiciary
    0.42
    Activations Density 0.003%

    No Known Activations