© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 104380
    Prev
    Next
    INDEX
    Explanations

    proper headers, future really, dual pathway

    np_acts-logits-general · gemini-2.5-flash-lite

    sections and categories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     אחד
    0.46
     κάτι
    0.44
    暗示
    0.44
     फिजिकल
    0.43
     برخی
    0.43
     خلق
    0.43
    ਓ
    0.43
    βολ
    0.42
    jda
    0.41
    bole
    0.41
    POSITIVE LOGITS
     columnspan
    0.43
     flowed
    0.42
     Implement
    0.40
    ম
    0.40
    েন
    0.39
     decreed
    0.39
     প্রতিষ্ঠিত
    0.39
    ري
    0.38
     Susan
    0.38
     quaternion
    0.38
    Activations Density 0.000%

    No Known Activations