© 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. 44055
    Prev
    Next
    INDEX
    Explanations

    VPN, rheumatoid

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

    prefixes, DIY, regeneration, summarizes

    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
    하고
    0.52
    或
    0.49
     или
    0.49
     في
    0.48
     compro
    0.47
    奀
    0.47
     حتى
    0.46
     courtes
    0.46
     در
    0.45
     despite
    0.45
    POSITIVE LOGITS
    backslash
    0.50
     করিতেছিল
    0.50
    ra
    0.50
    timeout
    0.50
    package
    0.50
     आर्टिकल
    0.49
     थोड़ा
    0.49
    mdp
    0.48
    চ্ছিলাম
    0.48
    4
    0.47
    Activations Density 0.000%

    No Known Activations