© 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. 57656
    Prev
    Next
    INDEX
    Explanations

    welcome to ourwelcome to the

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

    learning about emotions or actions

    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
     कृति
    0.55
     கண்டிப்பாக
    0.49
     документ
    0.48
    war
    0.47
     منطقة
    0.47
    lád
    0.46
     式
    0.45
     която
    0.45
    path
    0.44
     جميلة
    0.44
    POSITIVE LOGITS
    Facebook
    0.48
    Deserialize
    0.48
    ترین
    0.45
    Discrimin
    0.44
    Simulator
    0.44
    ઁ
    0.43
    Graduate
    0.43
     közel
    0.42
    ListenAnd
    0.42
    ခဲ့
    0.42
    Activations Density 0.000%

    No Known Activations