© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 1759
    Prev
    Next
    INDEX
    Explanations

    physicality

    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
    becue
    0.98
    hetic
    0.95
    èng
    0.90
    cherry
    0.88
    wein
    0.88
    cope
    0.84
    æ
    0.82
    wooden
    0.82
    vos
    0.81
    oble
    0.81
    POSITIVE LOGITS
     onRouteChange
    1.19
     homeostasis
    1.08
     
    1.04
     Pharmacol
    1.03
     Erkrank
    1.02
     生命周期
    1.02
     상승
    1.01
    𒊏
    1.00
     unmittel
    1.00
     BMI
    1.00
    Activations Density 0.076%

    No Known Activations