© 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-65K
    7. 46666
    Prev
    Next
    INDEX
    Explanations

    RGB color tuples

    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_65k_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
    ᕈ
    0.50
    ራ
    0.48
    ravings
    0.44
    禳
    0.43
     unve
    0.42
     sinner
    0.41
    няка
    0.41
    ****",
    0.41
    FlashValue
    0.40
     бет
    0.40
    POSITIVE LOGITS
    Language
    0.41
     decomp
    0.41
     storyboard
    0.39
    呠
    0.38
     Launch
    0.37
     seen
    0.37
     Restart
    0.37
     debuting
    0.36
     defined
    0.36
    calculate
    0.36
    Activations Density 0.007%

    No Known Activations