© 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. 5453
    Prev
    Next
    INDEX
    Explanations

    predicting following words

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

    social media questions recommendations

    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
     yalnızca
    0.60
    *,
    0.59
     परिणामस्वरूप
    0.58
     hinsichtlich
    0.57
    ®,
    0.57
     يُ
    0.56
    ™,
    0.55
    诸多
    0.55
     inextricably
    0.55
     nahezu
    0.55
    POSITIVE LOGITS
     बच्चो
    0.85
     lvl
    0.79
     cuz
    0.77
     اخر
    0.77
    してる
    0.76
     alot
    0.72
     everytime
    0.71
     उसमे
    0.71
     xray
    0.70
     yamaha
    0.70
    Activations Density 0.271%

    No Known Activations