© 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. 7-GEMMASCOPE-2-RES-16K
    7. 14493
    Prev
    Next
    INDEX
    Explanations

    chrome.action.onClicked

    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_7_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
    ه
    3.69
    i
    3.15
    ి
    3.04
    a
    2.70
    ​
    2.50
    る
    2.34
    ে
    2.23
    ați
    2.23
    ை
    2.21
    ಿ
    2.14
    POSITIVE LOGITS
    𝐭
    3.22
    AppDesigner
    3.21
    𝐨
    3.14
    𝐞
    3.06
    𝐡
    2.84
    крема
    2.74
    PluginResult
    2.72
    ことができる
    2.66
    icier
    2.65
    ا
    2.61
    Activations Density 0.002%

    No Known Activations