© 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
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 2
    Prev
    Next
    INDEX
    Explanations

    links to resources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    сь
    1.50
    gan
    1.35
    glers
    1.31
    ]]]
    1.29
    lig
    1.27
    lat
    1.26
    ven
    1.25
    onation
    1.23
    \
    1.23
    la
    1.22
    POSITIVE LOGITS
    場合
    1.64
    ン
    1.64
    ériences
    1.60
     diferenças
    1.59
     प्रोवाइड
    1.59
     degrés
    1.54
     intitulé
    1.54
     पोहो
    1.52
     reconocido
    1.51
     przedsiębior
    1.50
    Activations Density 0.173%

    No Known Activations