© 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. 51121
    Prev
    Next
    INDEX
    Explanations

    ** Win + M: commands

    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
    脈
    0.41
    ूड
    0.41
     paradigma
    0.41
     gula
    0.40
    ստ
    0.40
    脉
    0.40
     όλ
    0.39
    棘
    0.39
    嚼
    0.39
     laminar
    0.38
    POSITIVE LOGITS
    you
    0.51
    why
    0.47
     forbindelse
    0.45
    when
    0.43
     knih
    0.42
    ِن
    0.42
    nYou
    0.42
     ketika
    0.41
     nedenle
    0.41
     enables
    0.41
    Activations Density 0.025%

    No Known Activations