© 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. 13-GEMMASCOPE-2-RES-65K
    7. 732
    Prev
    Next
    INDEX
    Explanations

    tú or ; followed by punctuation

    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_65k_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
    ete
    2.68
    oshop
    2.33
    ett
    2.17
    eted
    2.14
    ization
    2.13
    欖
    2.10
    ets
    2.02
    ese
    2.01
    indrome
    2.00
    ized
    2.00
    POSITIVE LOGITS
    s
    3.46
    sion
    2.92
    т
    2.81
    san
    2.51
    sens
    2.36
    sü
    2.27
    ゅ
    2.24
    sul
    2.23
    sap
    2.21
     이는
    2.20
    Activations Density 0.107%

    No Known Activations