© 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. 78026
    Prev
    Next
    INDEX
    Explanations

    allocation and choices

    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
     misfortunes
    0.44
     czł
    0.43
     gönder
    0.43
     dukkham
    0.42
    ';"+
    0.42
     وارد
    0.41
     attaque
    0.41
     கா
    0.40
    ḏ
    0.40
    alkoz
    0.40
    POSITIVE LOGITS
    จ
    0.47
     SCAN
    0.47
     differentiating
    0.47
     হাউ
    0.46
    া
    0.46
    以
    0.46
    闶
    0.45
    пыт
    0.44
    で
    0.44
    nelle
    0.44
    Activations Density 0.004%

    No Known Activations