© 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. 13408
    Prev
    Next
    INDEX
    Explanations

    startup costs and failures

    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
    .??"]
    2.53
    𒄭
    2.50
    <unused81>
    2.49
     renderEncoder
    2.48
     spacerItem
    2.45
    ꔰ
    2.43
     callSettings
    2.41
    𒐸
    2.40
    <unused1317>
    2.40
    ExpNow
    2.39
    POSITIVE LOGITS
    ا
    2.35
    t
    1.93
    u
    1.74
    aphys
    1.70
      
    1.62
    uole
    1.59
    rans
    1.58
    re
    1.57
     kter
    1.55
    ع
    1.52
    Activations Density 0.081%

    No Known Activations