© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 14637
    Prev
    Next
    INDEX
    Explanations

    errors, mixtures, and technical terms

    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_13_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
    ા
    3.05
    м
    3.04
    o
    3.00
    y
    2.83
    ۰
    2.75
    न
    2.66
    ه
    2.64
    a
    2.64
    en
    2.60
    ಿ
    2.58
    POSITIVE LOGITS
    𝐧
    2.74
    𝐚
    2.33
    ﺑ
    2.23
    aping
    2.21
    ymin
    2.20
    𝐞
    2.13
     />}
    2.13
    ﺳ
    2.08
    𝐫
    2.06
    𝐬
    2.05
    Activations Density 0.032%

    No Known Activations