© 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. 17-GEMMASCOPE-2-RES-16K
    7. 845
    Prev
    Next
    INDEX
    Explanations

    let's break down

    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_17_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
    ⇒
    1.07
    mystery
    1.03
    →
    1.02
    obje
    0.99
    soph
    0.98
    interpol
    0.98
    interpr
    0.98
    maur
    0.97
    numer
    0.95
    ❤
    0.94
    POSITIVE LOGITS
     Main
    1.33
     Settings
    1.24
     Client
    1.19
     Session
    1.18
     Stadium
    1.14
     MainPage
    1.13
     Coordinator
    1.13
     Setting
    1.09
     Registration
    1.09
     Tracker
    1.09
    Activations Density 0.189%

    No Known Activations