© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 205364
    Prev
    Next
    INDEX
    Explanations

    European Portuguese, deadline, cappuccino

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    拗
    0.48
    서트
    0.47
    提案
    0.46
    移
    0.46
     increíble
    0.45
    ちゃん
    0.44
    CANCEL
    0.44
    legacy
    0.44
    关键
    0.43
    longest
    0.43
    POSITIVE LOGITS
    heed
    0.46
     пок
    0.46
     пу
    0.45
     ва
    0.45
     वेब
    0.44
    istor
    0.43
    arini
    0.43
     Я
    0.42
     раз
    0.41
    ផ្ស
    0.41
    Activations Density 0.001%

    No Known Activations