© 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. 27288
    Prev
    Next
    INDEX
    Explanations

    last approved wedding App potential

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

    processes and approved states

    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
    AN
    0.54
    TI
    0.54
    Z
    0.54
    MIN
    0.52
    From
    0.52
    JI
    0.52
    INA
    0.51
     الرقم
    0.51
    oz
    0.50
    Ph
    0.49
    POSITIVE LOGITS
    ക്കള
    0.51
    퀘
    0.46
    кса
    0.46
     cracks
    0.46
     weaponry
    0.46
    корд
    0.45
     cracking
    0.45
     gyne
    0.44
    ^{+}(
    0.44
    éseket
    0.44
    Activations Density 0.000%

    No Known Activations