© 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-262K
    7. 51608
    Prev
    Next
    INDEX
    Explanations

    estimated travel times

    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_262k_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
     Williams
    0.44
    APAC
    0.43
    أ
    0.40
     Metro
    0.40
    Williams
    0.40
    c
    0.39
    New
    0.39
     Magazine
    0.39
    v
    0.39
     Miami
    0.39
    POSITIVE LOGITS
     eksp
    0.54
    die
    0.49
     kern
    0.48
     esperienza
    0.48
     kekuatan
    0.47
     kriy
    0.47
     banyaknya
    0.46
     die
    0.46
    ulları
    0.46
     egalitarian
    0.46
    Activations Density 0.004%

    No Known Activations