© 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
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 17262
    Prev
    Next
    INDEX
    Explanations

    @param and return tags

    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
    кових
    0.57
    ствии
    0.55
    ющихся
    0.55
    ਮ
    0.55
     മാ
    0.54
    ਵੀ
    0.54
     반영
    0.52
     상
    0.52
    exponential
    0.51
    aktif
    0.50
    POSITIVE LOGITS
     hurt
    0.61
     può
    0.54
     może
    0.53
     rua
    0.53
     thuốc
    0.52
     scar
    0.51
     raid
    0.51
     Hurt
    0.51
     Ass
    0.50
     raided
    0.50
    Activations Density 0.006%

    No Known Activations