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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 2523
    Prev
    Next
    INDEX
    Explanations

    cultural contexts

    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
    дцать
    3.35
    𝚎
    3.05
     t
    2.81
    ிற்கு
    2.80
    ĩnh
    2.74
    eli
    2.69
    琶
    2.65
    𝕕
    2.64
    𝕞
    2.62
    WriteLine
    2.62
    POSITIVE LOGITS
    er
    6.40
    y
    5.75
    ا
    5.68
    e
    5.46
    ০
    5.37
    る
    5.24
    ი
    5.24
    ה
    5.21
    י
    5.20
    ي
    5.01
    Activations Density 0.461%

    No Known Activations