© 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. 2625
    Prev
    Next
    INDEX
    Explanations

    date and time ranges

    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
    х
    1.44
     setMessage
    1.28
     setError
    1.24
    Malley
    1.21
    淆
    1.20
    nak
    1.15
    忑
    1.15
    ะ
    1.15
     спу
    1.09
     stderr
    1.09
    POSITIVE LOGITS
    ,【
    1.59
    ables
    1.59
     exclusions
    1.57
    ⁄
    1.57
     │
    1.51
     Produto
    1.49
    ப்பழ
    1.48
     Appart
    1.47
    ₃
    1.47
    𝔞
    1.47
    Activations Density 0.005%

    No Known Activations