© 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. 253518
    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
     文件
    0.58
     শাস্ত্র
    0.54
     имя
    0.50
     wnętr
    0.50
    亣
    0.50
     woorden
    0.50
     餐
    0.50
     入れ
    0.49
     পরবর্ত
    0.49
     亠
    0.49
    POSITIVE LOGITS
    ガネ
    0.46
    ８
    0.45
    S
    0.44
    stal
    0.43
    8
    0.43
    ハー
    0.43
    IPA
    0.41
    x
    0.41
    SEN
    0.40
     fuses
    0.40
    Activations Density 0.001%

    No Known Activations