© 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. 105143
    Prev
    Next
    INDEX
    Explanations

    legal and technical abbreviations

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

    mathematics and logic

    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
    Tr
    0.55
     get
    0.54
    #
    0.54
    Read
    0.53
    {
    0.53
     do
    0.52
    e
    0.50
    0
    0.50
    I
    0.50
    "
    0.49
    POSITIVE LOGITS
    સભા
    0.54
    sunline
    0.54
     谢
    0.54
     पीले
    0.54
    セキュリティ
    0.52
     სტ
    0.52
    adil
    0.52
     Гульнявыя
    0.52
     सम्मेलन
    0.52
    ²',
    0.52
    Activations Density 0.000%

    No Known Activations