© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 44868
    Prev
    Next
    INDEX
    Explanations

    foreign words and outcomes

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

    predictive maintenance

    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
    adikan
    0.48
    אנ
    0.48
    ODO
    0.47
     rubbed
    0.47
     viewed
    0.45
    жит
    0.45
    ᄐ
    0.44
    ремя
    0.44
    ண
    0.44
    ף
    0.43
    POSITIVE LOGITS
    muse
    0.53
    ligo
    0.53
     সুরক্ষিত
    0.50
     Sä
    0.49
     Armee
    0.49
    être
    0.48
     Esse
    0.48
     Größe
    0.47
    ête
    0.47
     موس
    0.47
    Activations Density 0.000%

    No Known Activations