© 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. 13691
    Prev
    Next
    INDEX
    Explanations

    sequence of letters

    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
    <unused901>
    1.80
     llrp
    1.75
    <unused2218>
    1.74
    <0x0F>
    1.73
    jahter
    1.73
    UtcNow
    1.71
    localVarHTTP
    1.68
     vutto
    1.68
    <unused1881>
    1.67
    
    1.67
    POSITIVE LOGITS
     may
    1.63
     as
    1.43
    ↵↵
    1.40
    न
    1.38
     더
    1.38
     more
    1.31
    더
    1.28
    may
    1.27
     even
    1.23
    P
    1.22
    Activations Density 0.282%

    No Known Activations