© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 26971
    Prev
    Next
    INDEX
    Explanations

    technical, medical, or legal entities

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

    acronyms, abbreviations, and specialized terminology in academic and technical 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_22/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
     its
    -0.94
    őre
    -0.91
     ","
    -0.85
    ками
    -0.84
     re
    -0.83
    ônus
    -0.83
     Universitäts
    -0.81
    {\
    -0.79
    });
    -0.79
    }_{
    -0.78
    POSITIVE LOGITS
     cortina
    0.96
    șit
    0.93
     seigneur
    0.92
     autres
    0.90
     otros
    0.88
    iterrane
    0.88
     сказ
    0.85
    켠
    0.84
    Inhalt
    0.82
     読む
    0.82
    Activations Density 0.509%

    No Known Activations