© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 215090
    Prev
    Next
    INDEX
    Explanations

    noticed something

    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_40_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
     ukulele
    0.43
    OGRAPH
    0.41
    Monkey
    0.40
     Skyscanner
    0.39
    春秋
    0.39
    Artista
    0.39
    ፍ
    0.38
     strollers
    0.38
     तीसरी
    0.38
     የሆነ
    0.37
    POSITIVE LOGITS
    宕
    0.39
    倬
    0.37
    games
    0.36
     Commanding
    0.35
    وَ
    0.35
     라이
    0.35
    页
    0.35
     gover
    0.34
     attendant
    0.34
    ந்தோ
    0.34
    Activations Density 0.001%

    No Known Activations