© 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. 24163
    Prev
    Next
    INDEX
    Explanations

    social network

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

    tracking individuals, less known, hyperlocal references

    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
     bygone
    0.52
    ACH
    0.51
    🥴
    0.49
    std
    0.48
    QWidget
    0.48
     २०२२
    0.47
    ग्रेड
    0.46
    ma
    0.46
     मरने
    0.46
    ंदे
    0.46
    POSITIVE LOGITS
    ر
    0.52
     Jü
    0.51
    ل
    0.47
     stromal
    0.47
    祿
    0.45
     Tumor
    0.45
    لاف
    0.45
    靈
    0.45
    參與
    0.44
    ித்து
    0.44
    Activations Density 0.000%

    No Known Activations