© 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-65K
    7. 56017
    Prev
    Next
    INDEX
    Explanations

    code block delimiters

    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
     стро
    0.48
     string
    0.48
     wint
    0.44
     rural
    0.43
     fibrils
    0.42
    性
    0.41
     strings
    0.41
     potassium
    0.40
     större
    0.40
     CBC
    0.40
    POSITIVE LOGITS
     सीतार
    0.49
     रक्षाबंधनाच्या
    0.46
     disassemble
    0.45
    改装
    0.44
     commande
    0.43
    杼
    0.43
    בד
    0.42
     organizer
    0.42
    崠
    0.40
    čaj
    0.40
    Activations Density 0.002%

    No Known Activations