© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 46809
    Prev
    Next
    INDEX
    Explanations

    need to know context

    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
     finden
    0.45
    &\
    0.45
     menyediakan
    0.43
    ॑
    0.43
    हेही
    0.43
    Visible
    0.43
    Ω
    0.42
     위한
    0.41
    Ι
    0.41
    І
    0.41
    POSITIVE LOGITS
    揚
    0.38
    sprogram
    0.37
     pork
    0.36
     पारी
    0.35
    ংশের
    0.34
    closePath
    0.34
    tti
    0.34
     Township
    0.34
    উল
    0.34
     Whit
    0.33
    Activations Density 0.000%

    No Known Activations