© 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. 20192
    Prev
    Next
    INDEX
    Explanations

    reduction and percentages

    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
    ynchronous
    0.51
    وہ
    0.48
    ளுடைய
    0.48
     샘
    0.45
    ૩
    0.45
     verwend
    0.44
     dette
    0.44
     congén
    0.44
     समझे
    0.44
    kan
    0.44
    POSITIVE LOGITS
    DAO
    0.48
     azalt
    0.47
    ከል
    0.46
    ลด
    0.44
    ㅋ
    0.44
    Reducer
    0.43
    स्तों
    0.42
    Reduce
    0.42
    Razor
    0.41
     grills
    0.41
    Activations Density 0.001%

    No Known Activations