© 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. 7038
    Prev
    Next
    INDEX
    Explanations

    software products or areas

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

    websites to, plumbing systems, damaged”, Republic was, need to, seamlessly *, kcal *

    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
    ='$
    0.46
    icmp
    0.45
    うちに
    0.45
    inė
    0.44
    विड़
    0.44
    =((
    0.44
    ぞ
    0.43
     leadership
    0.42
    adio
    0.42
    ican
    0.41
    POSITIVE LOGITS
     вари
    0.43
     {
    0.42
    STYLE
    0.41
    خته
    0.40
    Had
    0.40
     Ramsay
    0.40
    ppy
    0.39
    風格
    0.39
     crayons
    0.39
    风格
    0.39
    Activations Density 0.001%

    No Known Activations