© 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. 112913
    Prev
    Next
    INDEX
    Explanations

    government and international affairs

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

    advantageous arguments, with reasons

    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
    ،
    0.52
    ,
    0.49
     olup
    0.47
     of
    0.46
     yanlış
    0.46
     şu
    0.45
    ِ
    0.44
     ş
    0.43
     modest
    0.43
     meagre
    0.43
    POSITIVE LOGITS
     তারাই
    0.58
    会い
    0.57
    например
    0.55
    例えば
    0.49
     Например
    0.49
     शकतात
    0.48
    一樣
    0.48
    सरकार
    0.48
     পাকিস্তানীরা
    0.47
    比如
    0.47
    Activations Density 0.001%

    No Known Activations