© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 58613
    Prev
    Next
    INDEX
    Explanations

    HHV reactivation

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

    letter combinations "hh" or similar syllables in technical or programming contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    Pics
    -0.79
     ais
    -0.70
     nytt
    -0.65
     nuit
    -0.65
    eger
    -0.64
     mümkün
    -0.63
    طع
    -0.63
     Franti
    -0.63
     Damas
    -0.63
     isomorphism
    -0.62
    POSITIVE LOGITS
     छ
    0.93
    颚
    0.84
     QQ
    0.83
     ছ
    0.81
     Amish
    0.79
    ensuche
    0.79
    छ
    0.79
    minutos
    0.79
     urmă
    0.77
    🏟
    0.77
    Activations Density 0.031%

    No Known Activations