© 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. 259679
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     бере
    0.54
     предполагает
    0.47
     lichen
    0.46
     reflects
    0.45
     ferries
    0.45
    の研究
    0.44
    疸
    0.44
    ᱼ
    0.44
    實在
    0.44
     staples
    0.43
    POSITIVE LOGITS
    </
    0.48
    맘
    0.48
     όχι
    0.45
    awać
    0.44
    equalsIgnoreCase
    0.44
     บ้าง
    0.43
    帜
    0.42
    asi
    0.42
    NotBlank
    0.42
    ipasi
    0.41
    Activations Density 0.000%

    No Known Activations