© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 7605
    Prev
    Next
    INDEX
    Explanations

    you followed by suggestions

    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_22_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
     меда
    0.89
     dolce
    0.86
     tumb
    0.86
    还好
    0.85
    ovati
    0.84
    쯤
    0.81
     رموز
    0.80
     subtlety
    0.78
    甘
    0.78
     sweetest
    0.77
    POSITIVE LOGITS
     dissatisfied
    0.89
     disapproved
    0.83
     faulted
    0.82
     disapp
    0.82
    ians
    0.81
     dissatisfaction
    0.81
    ian
    0.80
     deficiency
    0.80
    anol
    0.78
    িয়ান
    0.77
    Activations Density 0.106%

    No Known Activations