© 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. 1001
    Prev
    Next
    INDEX
    Explanations

    is a, is the

    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
    <unused1936>
    1.69
    evaluate
    1.67
     ActivityCompat
    1.66
    filtering
    1.65
    <unused1173>
    1.64
    <unused1237>
    1.61
     canaliculato
    1.60
    <unused1197>
    1.60
    StudentRecord
    1.60
     adegu
    1.60
    POSITIVE LOGITS
     Es
    1.27
     T
    1.25
     es
    1.24
     et
    1.21
    man
    1.20
    me
    1.20
    Es
    1.19
     Shipbuilding
    1.19
    andra
    1.18
    őd
    1.17
    Activations Density 1.105%

    No Known Activations