© 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. 228619
    Prev
    Next
    INDEX
    Explanations

    currently unavailable, security services

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ₃
    0.56
    رش
    0.48
    不等
    0.45
     বদি
    0.44
     वर्दी
    0.44
    Assignments
    0.44
    \}}
    0.44
    стить
    0.43
     conquering
    0.43
     assignments
    0.42
    POSITIVE LOGITS
     breakaway
    0.49
    하기
    0.47
     Rowling
    0.45
     Schnee
    0.44
     DJI
    0.44
     Fitbit
    0.44
    لاميذ
    0.43
     كرد
    0.43
     Larson
    0.43
    귤
    0.42
    Activations Density 0.000%

    No Known Activations