© 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. 121885
    Prev
    Next
    INDEX
    Explanations

    statutory ruling, to them, any the

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

    non-English 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
    Not in Any Lists

    No Comments

    Negative Logits
     savait
    0.48
    sliced
    0.48
    towards
    0.46
     !")
    0.45
     !”
    0.44
     attenzione
    0.44
     !
    0.43
    til
    0.43
     législ
    0.43
    leaved
    0.43
    POSITIVE LOGITS
    atação
    0.46
     Conversely
    0.45
    艰
    0.41
    纾
    0.40
    이고
    0.40
     얘기
    0.40
    АР
    0.39
    Conversely
    0.39
    нет
    0.39
    АН
    0.39
    Activations Density 0.005%

    No Known Activations