© 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. 562
    Prev
    Next
    INDEX
    Explanations

    quoted terms

    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
     laid
    1.78
     gest
    1.78
     pur
    1.66
     usu
    1.52
     hold
    1.48
     unt
    1.42
    鳅
    1.41
     organ
    1.41
     pon
    1.41
    ევე
    1.40
    POSITIVE LOGITS
    ”）
    2.20
    }"
    2.18
    ->"
    2.10
    %"
    2.08
    ()"
    1.89
    ")
    1.88
    "]
    1.88
    şı
    1.86
    Todos
    1.86
    ]"
    1.84
    Activations Density 0.305%

    No Known Activations