© 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. 45186
    Prev
    Next
    INDEX
    Explanations

    distinguish, between, via

    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
     exemples
    0.54
     выступления
    0.52
     денег
    0.51
    尃
    0.51
     เช่น
    0.50
    庝
    0.50
     doings
    0.49
    谤
    0.49
     других
    0.49
     계속
    0.48
    POSITIVE LOGITS
     between
    0.57
     UNESCO
    0.56
     Sauvignon
    0.53
     terroir
    0.51
     Chardonnay
    0.51
    0.50
     sediment
    0.50
     quinoa
    0.49
    7
    0.48
     water
    0.48
    Activations Density 0.022%

    No Known Activations