© 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. 166420
    Prev
    Next
    INDEX
    Explanations

    advise, leather, pool,Sessions, rather, improper

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

    policy or without

    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
     veg
    0.50
    Alle
    0.45
     squash
    0.45
    Finding
    0.43
     branche
    0.43
    ↵
    0.43
     marché
    0.42
     combate
    0.42
     fertilizer
    0.42
     clamp
    0.41
    POSITIVE LOGITS
    uatu
    0.57
     არა
    0.56
     ရက်
    0.54
    ຢ່າງ
    0.53
     하며
    0.52
     አንዳንድ
    0.51
    ჲ
    0.51
     አል
    0.50
    assapi
    0.50
    asText
    0.50
    Activations Density 0.000%

    No Known Activations