© 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. 13036
    Prev
    Next
    INDEX
    Explanations

    attributes, personal qualities, yourselves

    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
    𝘃
    2.65
     skilled
    2.64
    <unused716>
    2.61
    iencia
    2.51
    𝗲
    2.50
    𝗶
    2.49
    ে
    2.38
    𝗮
    2.37
    智慧
    2.35
    𝗿
    2.35
    POSITIVE LOGITS
    ma
    1.78
    آپ
    1.71
    ke
    1.70
    ۔
    1.69
    b
    1.66
    vorm
    1.66
    me
    1.65
    ücke
    1.63
    mente
    1.63
    bold
    1.61
    Activations Density 0.012%

    No Known Activations