© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 14041
    Prev
    Next
    INDEX
    Explanations

    Unilever, docker, terraform

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    C
    0.51
     ocho
    0.50
     renting
    0.49
     зер
    0.48
     DICK
    0.47
     到
    0.44
     ܘ
    0.43
    ட்டால்
    0.43
     pen
    0.41
     Объ
    0.41
    POSITIVE LOGITS
    நீர்
    0.50
    ियर
    0.47
    have
    0.44
     ऋतु
    0.42
    קס
    0.42
     কিছুটা
    0.42
    nutí
    0.41
    ₂+
    0.40
    vér
    0.40
    🥥
    0.40
    Activations Density 0.049%

    No Known Activations