© 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. 139623
    Prev
    Next
    INDEX
    Explanations

    tracking and analytics

    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
     theyre
    0.52
    انی
    0.52
     aloj
    0.49
     aparecer
    0.49
     oftent
    0.48
    贞
    0.48
     agrega
    0.48
     বণিক
    0.48
     mage
    0.48
    ون
    0.46
    POSITIVE LOGITS
    рили
    0.46
     Babu
    0.45
     Circuits
    0.45
    定量
    0.44
    insel
    0.43
     Hew
    0.42
    klärung
    0.42
     Pele
    0.42
     Mudd
    0.42
    鿁
    0.42
    Activations Density 0.001%

    No Known Activations