© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 4692
    Prev
    Next
    INDEX
    Explanations

    facial expressions and emojis

    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_16k_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
     senhores
    0.44
     connections
    0.44
     conversations
    0.43
     RESP
    0.42
     berita
    0.42
     vernacular
    0.42
    _______________
    0.42
     ferramenta
    0.40
    與
    0.40
     sentences
    0.40
    POSITIVE LOGITS
     wink
    0.48
     улы
    0.47
    smile
    0.46
     sourire
    0.44
     smiling
    0.43
     cringe
    0.43
    colorful
    0.42
    兴奋
    0.42
     smile
    0.42
     cười
    0.41
    Activations Density 0.085%

    No Known Activations