© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 204646
    Prev
    Next
    INDEX
    Explanations

    ask your question

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     naturally
    0.57
     teach
    0.48
     Kid
    0.45
    জ
    0.44
     teaches
    0.44
    it
    0.43
     Lewis
    0.42
     Naturally
    0.42
     get
    0.42
     Creative
    0.42
    POSITIVE LOGITS
     γιατί
    0.54
     заявление
    0.52
     ਦਵਾਈ
    0.51
    colo
    0.51
    瀕
    0.50
    âmara
    0.50
     Será
    0.49
     desliz
    0.49
     atténuées
    0.48
     activación
    0.48
    Activations Density 0.001%

    No Known Activations