© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 65739
    Prev
    Next
    INDEX
    Explanations

    units of measurement

    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_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
    Vegetables
    -1.23
     probablement
    -1.14
    others
    -1.13
     делает
    -1.13
     meeste
    -1.12
     aarde
    -1.12
    Ct
    -1.09
     embrague
    -1.07
    now
    -1.06
     取り付け
    -1.06
    POSITIVE LOGITS
     ago
    1.34
    fonds
    1.32
    blad
    1.19
    доба
    1.18
     ἀ
    1.18
    tiqueta
    1.16
     you
    1.16
     ὑ
    1.15
     вас
    1.13
     США
    1.12
    Activations Density 0.112%

    No Known Activations