© 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. 61023
    Prev
    Next
    INDEX
    Explanations

    for each month or number

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

    descriptions followed by a colon

    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
    č
    0.48
     conjunct
    0.45
    हे
    0.43
    ๋
    0.43
     conj
    0.42
     molecules
    0.42
     callbacks
    0.42
     prett
    0.41
     footprints
    0.41
     Centuries
    0.41
    POSITIVE LOGITS
     سپ
    0.52
     گو
    0.51
     система
    0.51
     ksi
    0.50
     স্প
    0.49
     می‌دهد
    0.49
    ៧
    0.48
    ികളും
    0.48
     系统
    0.47
     जीनत
    0.46
    Activations Density 0.000%

    No Known Activations