© 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. 14124
    Prev
    Next
    INDEX
    Explanations

    equalling or specific phrases

    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
    s
    3.03
    キュリティ
    2.93
    র
    2.61
    ের
    2.60
    ン
    2.47
    l
    2.44
    ათ
    2.43
    sberg
    2.43
    WindowEvent
    2.40
    ल
    2.40
    POSITIVE LOGITS
    которые
    2.84
    訕
    2.65
    जरीवाल
    2.37
    ey
    2.34
    jsxFileName
    2.33
    ścia
    2.31
    थमिक
    2.29
    ীব্র
    2.24
    Personensuche
    2.23
    𝗵
    2.19
    Activations Density 0.007%

    No Known Activations