© 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. 13-GEMMASCOPE-2-RES-16K
    7. 2597
    Prev
    Next
    INDEX
    Explanations

    save code

    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
    ｬ
    1.82
    萏
    1.79
    
    1.69
    межу
    1.69
     Uniform
    1.67
     zhī
    1.66
    sant
    1.65
     IDA
    1.64
     `:`
    1.64
    ्ट
    1.63
    POSITIVE LOGITS
    InstanceState
    3.00
    en
    2.46
    에
    2.02
    enka
    1.89
    ਂ
    1.89
    enal
    1.81
    enak
    1.79
    ادم
    1.77
    enek
    1.72
    ン
    1.69
    Activations Density 0.015%

    No Known Activations