© 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. 249608
    Prev
    Next
    INDEX
    Explanations

    after or ongoing events

    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
     সরে
    0.57
     crystalline
    0.46
     فی
    0.45
     well
    0.45
     থাকলে
    0.44
    成
    0.44
     rind
    0.44
    胶
    0.43
     excre
    0.43
     belongs
    0.42
    POSITIVE LOGITS
    avra
    0.57
    бль
    0.51
    nilvadipine
    0.50
     incentiv
    0.49
    一件
    0.48
     indiquer
    0.48
    忑
    0.48
     tentando
    0.47
    ScriptBuf
    0.47
     insuficiente
    0.47
    Activations Density 0.000%

    No Known Activations