© 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. 138402
    Prev
    Next
    INDEX
    Explanations

    Sources

    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
     includes
    0.40
    瘦
    0.39
    γμα
    0.38
     chutes
    0.38
    靗
    0.38
    梩
    0.38
    UNITY
    0.38
     ينت
    0.37
    實
    0.37
     shelter
    0.37
    POSITIVE LOGITS
     Coil
    0.40
     tuvieron
    0.40
    ỗi
    0.39
    glicherweise
    0.37
     copied
    0.37
     Printing
    0.37
    otyp
    0.37
    wider
    0.37
    データの
    0.36
    コピー
    0.36
    Activations Density 0.008%

    No Known Activations