© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 90957
    Prev
    Next
    INDEX
    Explanations

    dental hygiene or teeth whitening

    np_acts-logits-general · gemini-2.5-flash-lite

    exploring options for a new initiative

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     выбо
    0.44
     drier
    0.42
     இந்தப்
    0.42
    ズ
    0.40
     منظم
    0.40
    辺
    0.40
    빈
    0.40
    вален
    0.39
    ങ്ങള്‍ക്ക്
    0.39
    ያዎች
    0.39
    POSITIVE LOGITS
     ony
    0.47
     renounce
    0.46
    眹
    0.45
    StateToProps
    0.44
     hatta
    0.44
     lernen
    0.44
    惭
    0.43
    Ꮋ
    0.43
    रानी
    0.42
     KAP
    0.41
    Activations Density 0.000%

    No Known Activations