© 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. 22-GEMMASCOPE-RES-131K
    7. 15391
    Prev
    Next
    INDEX
    Explanations

    citations and chemical/biotech abbreviations

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

    citation references in academic papers, particularly those in brackets with journal abbreviations.

    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
     descargar
    -1.18
    Rather
    -1.16
    Any
    -1.13
    Generally
    -1.11
    Anyone
    -1.05
    cshtml
    -1.05
    *}[
    -1.02
    Initially
    -1.02
    Now
    -1.02
    Once
    -1.02
    POSITIVE LOGITS
    NSNotification
    1.04
     разные
    0.98
    OptionPane
    0.98
     mentioned
    0.91
     hefyd
    0.88
     not
    0.87
     zelfs
    0.87
     raggiung
    0.85
    lichen
    0.84
    說的
    0.84
    Activations Density 0.006%

    No Known Activations