© 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. 1599
    Prev
    Next
    INDEX
    Explanations

    feedback loop, blow

    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
     and
    1.43
     has
    1.43
     以及
    1.30
     ア
    1.26
     had
    1.26
     admired
    1.26
     그리고
    1.25
     サ
    1.24
     có
    1.23
     Cl
    1.22
    POSITIVE LOGITS
    weapp
    1.50
    EXPECT
    1.39
    commun
    1.34
    proportion
    1.30
    PRIMARY
    1.30
    inducing
    1.27
    Popul
    1.27
    MODULE
    1.26
    स्पर
    1.26
    फेक्ट
    1.24
    Activations Density 0.014%

    No Known Activations