© 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-262K
    7. 54020
    Prev
    Next
    INDEX
    Explanations

    sadness or contrast

    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
     thicken
    0.40
     PLUS
    0.39
    Ла
    0.37
     labrador
    0.37
     และ
    0.37
    EXPER
    0.37
     jugo
    0.37
    笋
    0.36
    Lab
    0.36
    Fab
    0.36
    POSITIVE LOGITS
     Alas
    0.63
    可惜
    0.57
     alas
    0.52
     sadly
    0.50
     unfortunately
    0.50
     ἢ
    0.49
     Nevertheless
    0.48
     Nonetheless
    0.47
     Sadly
    0.47
     Unfortunately
    0.46
    Activations Density 0.063%

    No Known Activations