© 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. 35561
    Prev
    Next
    INDEX
    Explanations

    investing to purchase

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

    generating terrain

    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
    ر
    0.58
    عد
    0.52
    ریان
    0.52
    غ
    0.51
    ہ
    0.48
    ع
    0.47
    ון
    0.46
    ल
    0.46
    ہری
    0.45
    جرة
    0.44
    POSITIVE LOGITS
     দাত
    0.52
     খে
    0.47
    toBe
    0.47
     सच्ची
    0.47
     দান
    0.47
     スタッドレスタイヤ
    0.47
     কা
    0.47
     barometer
    0.47
     কাপ
    0.46
    ūsų
    0.46
    Activations Density 0.000%

    No Known Activations