© 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. 16-GEMMASCOPE-2-RES-262K
    7. 27132
    Prev
    Next
    INDEX
    Explanations

    encoder, decoder, cache, undercoat

    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_16_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
    en
    0.59
    an
    0.59
    4
    0.57
    ettiva
    0.55
     několika
    0.55
     زیرا
    0.54
    oarece
    0.53
    <0x0D>
    0.53
     zarówno
    0.53
    其他
    0.52
    POSITIVE LOGITS
     present
    0.49
     counsel
    0.46
    man
    0.45
    ने
    0.44
     gather
    0.44
     remand
    0.43
     accountants
    0.43
     apportionment
    0.43
     compulsive
    0.42
     gathering
    0.42
    Activations Density 0.012%

    No Known Activations