© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 3774
    Prev
    Next
    INDEX
    Explanations

    under King, a, the

    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
    3.22
    u
    2.99
    n
    2.68
    𝔬
    2.61
    िप्ट
    2.59
    ibly
    2.53
    পক্ষে
    2.50
    으로
    2.50
    ोग्रा
    2.47
    iliano
    2.45
    POSITIVE LOGITS
    Ｅ
    3.12
    ᆸ
    3.00
    ளாக்
    2.90
    ﮈ
    2.89
    Вот
    2.79
    INGS
    2.76
    Перед
    2.74
    Х
    2.73
    .".,
    2.68
    Ва
    2.64
    Activations Density 0.003%

    No Known Activations