© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 1162
    Prev
    Next
    INDEX
    Explanations

    python code generation

    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
    ാരി
    1.65
    菻
    1.62
     völl
    1.61
    𝙢
    1.59
    𝙜
    1.57
     경우가
    1.56
    Ħ
    1.55
    컹
    1.55
     nią
    1.54
    ㅌ
    1.54
    POSITIVE LOGITS
    stown
    1.50
    urved
    1.46
    encies
    1.41
    night
    1.40
    imba
    1.38
    ”
    1.38
    kes
    1.34
    eylon
    1.30
    day
    1.30
    em
    1.29
    Activations Density 0.090%

    No Known Activations