© 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. 29705
    Prev
    Next
    INDEX
    Explanations

    code function definitions

    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
     нём
    0.40
     głów
    0.36
     Watson
    0.35
    otional
    0.35
     výsled
    0.35
     scă
    0.35
    %)
    0.35
     aplicação
    0.35
    »)
    0.35
    ē
    0.34
    POSITIVE LOGITS
    یت
    0.45
     शुभ
    0.42
    ಯ
    0.41
     장
    0.40
    یم
    0.39
     여섯
    0.39
    𐱅
    0.38
     Umar
    0.38
    __[
    0.37
    __:
    0.37
    Activations Density 0.022%

    No Known Activations