© 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. 40-GEMMASCOPE-2-RES-65K
    7. 54533
    Prev
    Next
    INDEX
    Explanations

    dill pickles

    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_40_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
     subcl
    0.45
     الهمزه
    0.43
    FLY
    0.42
    𝜆
    0.42
     контек
    0.41
    悸
    0.41
    ㈠
    0.40
    컸
    0.39
     지역
    0.39
    
    0.39
    POSITIVE LOGITS
    ‰
    0.37
     following
    0.36
    äs
    0.36
    ginas
    0.36
     =
    0.35
     for
    0.35
    gui
    0.35
    ताव
    0.35
     inm
    0.35
    ů
    0.34
    Activations Density 0.000%

    No Known Activations