© 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. 50300
    Prev
    Next
    INDEX
    Explanations

    transportation, sequences, QM, string

    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
     detective
    0.44
    ඨ
    0.44
     fren
    0.44
    ොර
    0.43
     veze
    0.42
    ڃ
    0.41
     Consultado
    0.41
     tensions
    0.40
     protesters
    0.40
    taş
    0.40
    POSITIVE LOGITS
     phần
    0.51
    ח
    0.50
    ส่วน
    0.47
     الجزء
    0.42
     以及
    0.41
    零件
    0.41
     其他
    0.41
     তাছাড়া
    0.41
    να
    0.40
    的小
    0.40
    Activations Density 0.024%

    No Known Activations