© 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. 52037
    Prev
    Next
    INDEX
    Explanations

    worldwide shipping servicesspecialist document screeningglad you liked itreview for

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

    pencil skirt, education, weaver, fans

    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
    ocalypse
    0.45
    ค
    0.45
    acters
    0.45
    ート
    0.44
    哥
    0.44
    ando
    0.43
    д
    0.42
    梆
    0.42
    ped
    0.42
     ゴ
    0.42
    POSITIVE LOGITS
    尌
    0.55
    racht
    0.53
     aufgenommen
    0.51
     Bewer
    0.48
     عزت
    0.47
     contentment
    0.46
    reiche
    0.45
     ކ
    0.45
     Neben
    0.44
     ehemal
    0.44
    Activations Density 0.001%

    No Known Activations