© 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. 48938
    Prev
    Next
    INDEX
    Explanations

    tokens ending in da or a

    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
     nigh
    0.39
     envo
    0.36
     Rés
    0.36
     Показа
    0.36
     factor
    0.36
     wait
    0.35
     instruct
    0.35
    踊
    0.35
     overwhelmed
    0.34
    jorie
    0.34
    POSITIVE LOGITS
    紝
    0.45
    ISHING
    0.41
    żyć
    0.39
    빴
    0.39
    ዊ
    0.39
    ctions
    0.38
    рур
    0.38
    ILY
    0.38
    getBytes
    0.38
     কারন
    0.36
    Activations Density 0.011%

    No Known Activations