© 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. 164417
    Prev
    Next
    INDEX
    Explanations

    integrated green, viable companion, portable classrooms, China struggles

    np_acts-logits-general · gemini-2.5-flash-lite

    Orange Revolution

    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
    s
    0.52
    دي
    0.46
    ס
    0.45
    ді
    0.44
    d
    0.44
    蛋白
    0.44
    睒
    0.44
     కీలక
    0.44
    妻子
    0.43
    毒
    0.43
    POSITIVE LOGITS
     revoke
    0.49
    atham
    0.49
     nearing
    0.45
    atmosphere
    0.43
     sobbing
    0.42
    veranst
    0.42
     fibrous
    0.41
    getReference
    0.41
     बचें
    0.41
     पन
    0.41
    Activations Density 0.000%

    No Known Activations