© 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. 233804
    Prev
    Next
    INDEX
    Explanations

    specific keywords and punctuation

    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
     Schroeder
    0.43
     Forder
    0.42
    Twelve
    0.41
     पदाधिकारियों
    0.40
     jedin
    0.40
    ₱
    0.40
     Zucker
    0.40
    தாகவும்
    0.39
     oszt
    0.39
     постро
    0.38
    POSITIVE LOGITS
     सस्ते
    0.50
    不支持
    0.49
    কারণ
    0.48
    了一种
    0.47
    部分
    0.46
    未能
    0.46
    ፈ
    0.46
     unforeseen
    0.46
     विल
    0.46
    φο
    0.46
    Activations Density 0.001%

    No Known Activations