© 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. 255120
    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
    捪
    0.54
    ט
    0.49
    ký
    0.49
    工资
    0.47
    גו
    0.47
     दशमलव
    0.46
    ڈنگ
    0.46
    맟
    0.46
    Ро
    0.44
    quilibrium
    0.44
    POSITIVE LOGITS
     sizeable
    0.58
     unless
    0.48
     sizable
    0.48
     площад
    0.48
     neatly
    0.47
     plate
    0.46
     sock
    0.45
     plates
    0.44
     plugging
    0.44
     площа
    0.44
    Activations Density 0.000%

    No Known Activations