© 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. 170128
    Prev
    Next
    INDEX
    Explanations

    framed, life, agree, assays, spouse

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

    bond loan

    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
     sämt
    0.45
    ست
    0.41
     두
    0.40
     أكبر
    0.40
    영
    0.40
    瞭
    0.40
    業
    0.39
    Gü
    0.39
    CENT
    0.38
    炤
    0.38
    POSITIVE LOGITS
     pleasant
    0.51
    pleasant
    0.48
    galkan
    0.46
    arabangsa
    0.46
    nahi
    0.46
    nemen
    0.46
     remporté
    0.46
     初始化
    0.45
    वून
    0.45
     dour
    0.44
    Activations Density 0.001%

    No Known Activations