© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 241848
    Prev
    Next
    INDEX
    Explanations

    argue with, direct engagement, sports enthusiasts

    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
    יר
    0.45
     Monastery
    0.43
     disconcert
    0.43
    Haz
    0.43
    신
    0.43
     to
    0.43
     humanist
    0.42
    ினாலும்
    0.42
     apparently
    0.42
     resolute
    0.42
    POSITIVE LOGITS
     velocidade
    0.53
     gasolina
    0.51
     pembelian
    0.48
     obesidad
    0.48
    𝙜
    0.46
     caja
    0.45
     desafio
    0.45
     Einwill
    0.45
     kecepatan
    0.44
    快的
    0.44
    Activations Density 0.002%

    No Known Activations