© 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-65K
    7. 51598
    Prev
    Next
    INDEX
    Explanations

    metadata or encoding

    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_65k_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
    let
    0.51
    l
    0.47
    shi
    0.47
    azin
    0.47
    born
    0.46
    T
    0.46
    lys
    0.46
    ment
    0.45
    ama
    0.45
    verbal
    0.45
    POSITIVE LOGITS
     blijven
    0.60
    ى
    0.59
     vannak
    0.57
     économiques
    0.55
     œufs
    0.54
     slaughtered
    0.52
     rimane
    0.52
    ステージ
    0.52
    squre
    0.51
     américaine
    0.51
    Activations Density 0.001%

    No Known Activations