© 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. 146022
    Prev
    Next
    INDEX
    Explanations

    blog tour campaign

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

    formatting specifiers and code

    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
     ChatGPT
    0.40
     दरों
    0.40
     アウトドア
    0.40
     usada
    0.39
     comenzamos
    0.39
     ഉ
    0.39
     repurposed
    0.39
    ُوْ
    0.39
     voix
    0.38
     ريد
    0.38
    POSITIVE LOGITS
     AFRICA
    0.46
    extern
    0.43
    SHORT
    0.41
     interrelated
    0.41
     ECONOMIC
    0.41
    pending
    0.40
     CIRCA
    0.40
     TIMES
    0.40
    equal
    0.39
    framework
    0.39
    Activations Density 0.002%

    No Known Activations