© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 110559
    Prev
    Next
    INDEX
    Explanations

    Copyright notices

    np_acts-logits-general · gemini-2.5-flash-lite

    year tokens in copyright statements, particularly in the format "20XX".

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     are
    -2.05
     you
    -1.80
     Misalnya
    -1.59
    nossa
    -1.56
     zrobić
    -1.55
     nová
    -1.55
     Khusus
    -1.48
    merking
    -1.45
     potrebné
    -1.45
     sekarang
    -1.44
    POSITIVE LOGITS
    to
    1.71
    ↵↵
    1.61
     
    1.60
    0
    1.60
    from
    1.59
    €”
    1.55
    Never
    1.53
     каждом
    1.52
    できるだけ
    1.48
    in
    1.47
    Activations Density 0.085%

    No Known Activations