© 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. 169936
    Prev
    Next
    INDEX
    Explanations

    Nobel Prize

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

    explaining scopes and good qualifiers

    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
    ன
    0.46
    东
    0.46
     dissent
    0.45
     protesta
    0.45
    л
    0.45
    сев
    0.45
    ！
    0.45
    се
    0.44
    进了
    0.44
     otherworldly
    0.44
    POSITIVE LOGITS
    囑
    0.46
    Et
    0.46
    明顯
    0.45
    溫度
    0.45
    swering
    0.45
    Ethyl
    0.45
    EY
    0.44
     منذ
    0.44
    ku
    0.44
    佇
    0.44
    Activations Density 0.000%

    No Known Activations