© 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. 13-GEMMASCOPE-2-RES-16K
    7. 7895
    Prev
    Next
    INDEX
    Explanations

    stable equilibrium

    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_13_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
    remove
    2.16
    cumulative
    2.15
    𝒎
    2.06
    唤
    2.05
    ју
    2.04
    ोत्
    2.03
     लैंग्वेज
    2.00
     ख
    2.00
    directories
    1.98
    Arqu
    1.98
    POSITIVE LOGITS
     الصل
    1.66
    arity
    1.62
    tering
    1.60
    iteit
    1.59
     vững
    1.58
    asjon
    1.57
    uation
    1.50
     footing
    1.48
     نحل
    1.47
    coins
    1.44
    Activations Density 0.401%

    No Known Activations