© 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. 257272
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ტ
    0.49
     labb
    0.47
    ଛ
    0.46
     Attributes
    0.45
    介绍了
    0.45
    ാൻഡ്
    0.44
     禁止
    0.44
    pèce
    0.43
    Bian
    0.43
    ↥
    0.42
    POSITIVE LOGITS
     involuntary
    0.51
     crippling
    0.51
    つまり
    0.50
     multifaceted
    0.46
     injury
    0.45
     pharmacokinetic
    0.45
     фактически
    0.45
     crippled
    0.44
     enzymatic
    0.44
     необходимо
    0.43
    Activations Density 0.005%

    No Known Activations