© 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. 164128
    Prev
    Next
    INDEX
    Explanations

    ecosystem, IL, way, function

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

    introduces definitions or categories

    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
    抢
    0.54
    έσ
    0.52
    ώσει
    0.50
     আভ
    0.49
    BURTS
    0.47
     Geschäftsführer
    0.47
    গ
    0.46
    搶
    0.45
    পন্থী
    0.45
    乘坐
    0.45
    POSITIVE LOGITS
    ada
    0.53
     Mor
    0.51
     D
    0.51
     II
    0.51
    also
    0.50
    por
    0.49
    led
    0.49
    Mor
    0.48
    mor
    0.47
    ie
    0.47
    Activations Density 0.000%

    No Known Activations