© 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. 8735
    Prev
    Next
    INDEX
    Explanations

    visuals representing concepts

    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
     wszel
    0.46
     ప్రజా
    0.39
     demoral
    0.38
     precondition
    0.38
    certain
    0.38
     compuls
    0.37
    専
    0.37
     dement
    0.37
    Certain
    0.36
     为
    0.36
    POSITIVE LOGITS
    示意
    0.60
     모습
    0.55
     smiling
    0.54
     منظر
    0.45
     पहने
    0.45
    smiling
    0.44
    笑顔
    0.44
     izgled
    0.43
     காட்சி
    0.43
     micrograph
    0.43
    Activations Density 0.104%

    No Known Activations