© 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. 17781
    Prev
    Next
    INDEX
    Explanations

    locations, names, or lists

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

    loanwords, scientific, reduction

    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
     相
    0.58
     меж
    0.57
     管
    0.56
     поезд
    0.53
     पारस्परिक
    0.51
    __,
    0.51
     באופן
    0.50
    ivariate
    0.49
     نموذج
    0.48
     sinusoidal
    0.48
    POSITIVE LOGITS
    ندوق
    0.57
    闥
    0.49
    ्हान
    0.49
    芒果
    0.47
     escond
    0.47
     imprisoned
    0.46
    quando
    0.46
    ဒီ
    0.45
    ঞ্
    0.44
    ہیں
    0.44
    Activations Density 0.001%

    No Known Activations