© 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. 192595
    Prev
    Next
    INDEX
    Explanations

    CPA license

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

    emphasis markers and specific terms

    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
    지의
    0.51
    欧盟
    0.49
    ﹍
    0.48
     María
    0.47
    '[
    0.45
    嘟
    0.45
    围绕
    0.45
     oposición
    0.44
    铜
    0.44
     spinors
    0.44
    POSITIVE LOGITS
    afood
    0.45
    STR
    0.45
     അഭ
    0.44
    aktif
    0.43
    elve
    0.42
     newfound
    0.42
    él
    0.41
    JECT
    0.41
    spaced
    0.40
    akn
    0.40
    Activations Density 0.001%

    No Known Activations