© 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. 140027
    Prev
    Next
    INDEX
    Explanations

    watch over, ad support, tons of

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

    calisthenics, hiking, km

    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
    账
    0.52
     Umsatz
    0.47
     Brows
    0.44
     매출
    0.44
    肐
    0.43
     içinde
    0.43
     invoices
    0.43
     sosyal
    0.43
     Handlung
    0.43
     Veranstaltung
    0.42
    POSITIVE LOGITS
    Cable
    0.59
    can
    0.54
     पूर्व
    0.53
    je
    0.50
    PET
    0.50
    ζ
    0.48
    WE
    0.46
    Wire
    0.46
    Pere
    0.46
    jih
    0.46
    Activations Density 0.000%

    No Known Activations