© 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. 31187
    Prev
    Next
    INDEX
    Explanations

    Nha Trang, NHapi, NH(2), NH(4), NHCs

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

    chemical formulas and compounds with NH2 or similar nitrogen-hydrogen structures.

    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
    …！
    -0.93
    〜！
    -0.93
     aérea
    -0.93
    前は
    -0.90
    もあって
    -0.86
     billede
    -0.85
    لبوم
    -0.85
    petual
    -0.82
    cipe
    -0.81
    zono
    -0.81
    POSITIVE LOGITS
    preneurs
    0.84
     jednak
    0.81
    pid
    0.80
    […]
    0.80
    屋の
    0.79
    тера
    0.78
    🚰
    0.77
    bate
    0.77
    ้
    0.76
     perciò
    0.75
    Activations Density 0.005%

    No Known Activations