© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 104495
    Prev
    Next
    INDEX
    Explanations

    numbers followed by articles, common words, or punctuation

    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
     but
    -1.20
    申し上げます
    -1.16
    licante
    -1.09
    josé
    -1.06
     WOMAN
    -1.05
     nieuwe
    -1.05
    PETS
    -1.05
     flesta
    -1.04
     apsau
    -1.04
    饷
    -1.03
    POSITIVE LOGITS
    7
    1.25
    8
    1.24
     ț
    1.20
     erwähnten
    1.11
    ntä
    1.09
    Conjunto
    1.04
    何より
    1.03
    0
    1.02
    tening
    0.99
    成長
    0.98
    Activations Density 0.002%

    No Known Activations