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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 14596
    Prev
    Next
    INDEX
    Explanations

    ruby red, wine, colors

    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
    力的
    2.80
    र्ज
    2.42
    ಲ್ಯಾ
    2.41
    𝚝
    2.39
    𝒾
    2.28
    ೃಷ್ಣ
    2.28
    િંગ
    2.28
    र्मु
    2.27
    𝚎
    2.26
    empot
    2.24
    POSITIVE LOGITS
    ে
    4.44
    e
    4.31
    י
    4.16
    ept
    3.96
    ea
    3.59
    es
    3.49
    s
    3.30
    يارات
    3.22
    i
    3.21
    ece
    3.15
    Activations Density 0.049%

    No Known Activations