© 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. 256653
    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
     進
    0.52
     άλ
    0.51
     vorhand
    0.50
     उद्यान
    0.49
     VHS
    0.48
     chữ
    0.47
     samoglas
    0.47
     निधि
    0.45
    forestation
    0.44
     iskust
    0.44
    POSITIVE LOGITS
    M
    0.58
    ERS
    0.54
    ק
    0.51
    ت
    0.50
    C
    0.50
    B
    0.50
    LEY
    0.49
    Alright
    0.48
    ies
    0.46
    BO
    0.45
    Activations Density 0.001%

    No Known Activations