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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 12219
    Prev
    Next
    INDEX
    Explanations

    HTML element interaction

    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
     the
    -1.66
     arī
    -1.59
    為に
    -1.52
    ようです
    -1.46
     myös
    -1.31
    ことも
    -1.30
    ごとの
    -1.23
     izman
    -1.20
     også
    -1.18
     führte
    -1.17
    POSITIVE LOGITS
    がありますが
    1.49
    でしょうね
    1.45
     recomendable
    1.32
    って思
    1.28
     impecable
    1.25
     VIH
    1.25
     vinos
    1.23
    但这
    1.22
     monsieur
    1.20
     Colegio
    1.20
    Activations Density 0.011%

    No Known Activations