© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 3556
    Prev
    Next
    INDEX
    Explanations

    nGrams, duos, quadriple, dinucleotide

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

    technical terminology related to n-grams, tokenization, and text processing.

    oai_token-act-pair · claude-3-7-sonnet-20250219
    Triggered 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
    Negative Logits
    acknowled
    -1.11
     admit
    -1.10
     призна
    -0.98
     admitting
    -0.93
     acknowledge
    -0.92
     Acknowled
    -0.91
     admission
    -0.89
    bergen
    -0.88
     acknowledged
    -0.85
     admits
    -0.85
    POSITIVE LOGITS
     combinations
    1.05
    OfSize
    1.01
     NG
    0.98
     duo
    0.93
     ng
    0.91
     duos
    0.91
     quadru
    0.88
    uples
    0.87
     combination
    0.86
     quadri
    0.86
    Activations Density 0.053%

    No Known Activations