© 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. 128814
    Prev
    Next
    INDEX
    Explanations

    the presence of numerical or statistical tokens (counts, dates, editions, figures) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    firsts and marks

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     that
    -1.50
     through
    -1.38
     as
    -1.35
     those
    -1.24
     which
    -1.08
     helps
    -1.08
     various
    -1.06
    枚目
    -1.06
     there
    -1.05
     helping
    -1.05
    POSITIVE LOGITS
    ówek
    1.30
     första
    1.27
     hän
    1.24
     lần
    1.22
     فقط
    1.16
     nummer
    1.13
     parfü
    1.12
    盉
    1.10
     akti
    1.08
     heilig
    1.08
    Activations Density 0.046%

    No Known Activations