© 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. 40-GEMMASCOPE-2-RES-262K
    7. 212764
    Prev
    Next
    INDEX
    Explanations

    specific non-English words

    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_40_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
     and
    0.44
     mer
    0.43
     abstractions
    0.43
     dels
    0.40
     contingencies
    0.40
     der
    0.40
    ,
    0.40
     forfeiture
    0.40
     investigates
    0.39
     both
    0.39
    POSITIVE LOGITS
    亣
    0.48
     какую
    0.47
    নির্দিষ্ট
    0.46
     específ
    0.46
     específico
    0.45
     específica
    0.45
    autorité
    0.44
     específicas
    0.44
    某个
    0.44
     irgendwo
    0.44
    Activations Density 0.004%

    No Known Activations