© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 93642
    Prev
    Next
    INDEX
    Explanations

    face and facial

    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_262k_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
     aband
    0.59
     abandonar
    0.59
    rvGroup
    0.55
     hac
    0.52
     الميلاد
    0.51
     arn
    0.51
    یشن
    0.50
     }^{
    0.50
     çıktı
    0.50
     offrir
    0.49
    POSITIVE LOGITS
     face
    1.34
     Face
    1.34
    Face
    1.30
     facial
    1.29
     Faces
    1.21
     Facial
    1.20
    面
    1.16
     wajah
    1.14
     FACE
    1.13
     faces
    1.13
    Activations Density 0.063%

    No Known Activations