© 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. 251524
    Prev
    Next
    INDEX
    Explanations

    numbered or lettered lists

    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
    Greece
    0.43
    8
    0.42
    ദ്യോഗ
    0.41
    5
    0.41
    ням
    0.41
    3
    0.41
    Greek
    0.40
    am
    0.40
    nee
    0.39
    sext
    0.39
    POSITIVE LOGITS
    ️⃣
    0.46
     Saying
    0.44
     การ
    0.43
     veces
    0.40
     的
    0.40
     Việc
    0.40
     tempt
    0.40
    で
    0.40
     Would
    0.40
     trường
    0.40
    Activations Density 0.017%

    No Known Activations