© 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. 45142
    Prev
    Next
    INDEX
    Explanations

    children's stories and cartoons

    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
     покер
    0.48
    UED
    0.43
     সিগারেট
    0.42
    漬
    0.42
    তীর্থ
    0.42
     парамет
    0.42
     nightlife
    0.41
     ఛ
    0.41
    VIEW
    0.40
     극한
    0.40
    POSITIVE LOGITS
     children
    1.43
     Children
    1.32
     어린이
    1.32
    儿童
    1.28
    兒童
    1.25
     niños
    1.23
     kinderen
    1.22
    Children
    1.21
     crianças
    1.21
     childrens
    1.21
    Activations Density 0.206%

    No Known Activations