© 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-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 1570
    Prev
    Next
    INDEX
    Explanations

    closing eyes

    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
    GED
    1.38
    肦
    1.38
    osate
    1.31
    十玖章
    1.30
    ্ের
    1.30
    𒀯
    1.30
    ㄾ
    1.30
    शासित
    1.29
    𒄭
    1.29
    ANCIS
    1.28
    POSITIVE LOGITS
     fruitful
    1.20
     misfortune
    1.19
     prosperity
    1.19
     blissful
    1.19
    тельство
    1.17
     grace
    1.17
     Down
    1.10
     eat
    1.09
     sigmoid
    1.09
     gracious
    1.09
    Activations Density 0.003%

    No Known Activations