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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 32
    Prev
    Next
    INDEX
    Explanations

    running code or programs

    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
    èng
    0.85
    래
    0.82
    َيْ
    0.81
    ặp
    0.80
    ügen
    0.79
     बड़ा
    0.79
     یہ
    0.78
    般的
    0.76
    кій
    0.76
    û
    0.76
    POSITIVE LOGITS
     otherwise
    0.99
     wade
    0.83
     off
    0.83
     ong
    0.79
     dos
    0.77
    egd
    0.76
     er
    0.76
     ताकि
    0.75
     towards
    0.75
     step
    0.74
    Activations Density 0.083%

    No Known Activations