© 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. 10-GEMMASCOPE-RES-131K
    7. 127931
    Prev
    Next
    INDEX
    Explanations

    academic writing

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

    the presence of numeric expressions and count-related tokens (e.g. numbers and measurements).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     suave
    -1.39
    𖤍
    -1.38
     («
    -1.34
    鶿
    -1.31
     referrerpolicy
    -1.30
     paseo
    -1.27
    tų
    -1.23
    Postgres
    -1.23
    ismer
    -1.23
     hidupnya
    -1.23
    POSITIVE LOGITS
    .”
    1.56
     entwickelt
    1.55
     that
    1.55
     bewegt
    1.48
     verursacht
    1.48
     beendet
    1.41
     giúp
    1.38
     überrascht
    1.38
     integriert
    1.38
     berichtet
    1.36
    Activations Density 0.032%

    No Known Activations