© 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. 178702
    Prev
    Next
    INDEX
    Explanations

    package delivery issues

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

    psychology and abstract concepts

    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
    ร
    0.48
    หัส
    0.46
    嵘
    0.46
     primos
    0.46
    াঙ্গীর
    0.46
    เว็บไซต์
    0.44
     Hershey
    0.44
    াবেক
    0.44
    仙
    0.44
     lysosomes
    0.44
    POSITIVE LOGITS
    itek
    0.50
     electrically
    0.47
     شغله
    0.46
     transport
    0.45
    طيع
    0.45
     المقام
    0.45
     conveyance
    0.44
    طي
    0.43
     scaled
    0.43
    ionine
    0.43
    Activations Density 0.000%

    No Known Activations