© 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. 63704
    Prev
    Next
    INDEX
    Explanations

    legal and financial terms

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

    segmentation/division/junctions

    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
    Pres
    0.45
     teorías
    0.45
    )});
    0.45
     teoria
    0.45
     theory
    0.44
    ).
    0.44
     teori
    0.44
    撣
    0.44
     الحكومة
    0.43
     théorie
    0.42
    POSITIVE LOGITS
     subsections
    0.53
    相続
    0.52
     subsets
    0.51
    iectasis
    0.49
    junction
    0.48
     subdivisions
    0.48
    iliation
    0.47
     பல்கலைக்கழக
    0.47
    𝔬
    0.47
    km
    0.46
    Activations Density 0.000%

    No Known Activations