© 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-16K
    7. 9472
    Prev
    Next
    INDEX
    Explanations

    summarizing key differences

    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
    a
    1.53
    en
    1.51
    e
    1.32
    eig
    1.31
    ו
    1.27
    glo
    1.26
    場合に
    1.24
    場合の
    1.24
    안녕하십니까
    1.22
     libera
    1.21
    POSITIVE LOGITS
     aliphatic
    1.71
     conda
    1.65
     SDGs
    1.52
    anye
    1.47
     Sunak
    1.43
     '/',
    1.43
     lilac
    1.40
     タン
    1.39
    里的
    1.38
     inning
    1.37
    Activations Density 0.000%

    No Known Activations