© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 210
    Prev
    Next
    INDEX
    Explanations

    SQL query string

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
     och
    1.38
     `
    1.35
    interface
    1.25
     normal
    1.25
     alias
    1.21
    init
    1.21
    origin
    1.20
    base
    1.19
     ann
    1.18
     welche
    1.18
    POSITIVE LOGITS
    の
    2.82
    的
    2.71
    을
    2.36
    를
    2.26
    ゃ
    2.19
    ه
    2.19
    に
    2.18
    รษฐ
    2.18
    るのは
    2.16
    ское
    2.13
    Activations Density 0.372%

    No Known Activations