© 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. 30529
    Prev
    Next
    INDEX
    Explanations

    way to

    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
    t
    0.49
    Use
    0.45
     чтобы
    0.45
     Use
    0.44
     enables
    0.44
     ताकि
    0.44
     আঘাতে
    0.43
    Spatial
    0.42
     afin
    0.42
    ل
    0.42
    POSITIVE LOGITS
     karşınız
    0.44
     nidd
    0.42
    .|__
    0.41
     камер
    0.41
    ˟
    0.40
     aquel
    0.39
     chied
    0.39
     memperkenalkan
    0.39
    [multimodal]
    0.38
    estad
    0.38
    Activations Density 0.065%

    No Known Activations