© 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. 19504
    Prev
    Next
    INDEX
    Explanations

    swap and conversion

    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
    ారి
    0.59
    amię
    0.54
    心
    0.54
    自
    0.53
    archives
    0.52
    小物
    0.52
    جھ
    0.51
    长
    0.51
    anges
    0.51
    apunov
    0.50
    POSITIVE LOGITS
    },
    0.57
     sesuai
    0.57
     電動
    0.57
     harvest
    0.55
     permite
    0.55
     doivent
    0.55
     chacune
    0.55
     splice
    0.55
     jeder
    0.54
     paginate
    0.54
    Activations Density 0.001%

    No Known Activations