© 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
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 13797
    Prev
    Next
    INDEX
    Explanations

    date placeholders in templates

    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
     Αν
    1.86
     InputMaybe
    1.78
     Cơ
    1.78
     Bản
    1.76
     Hàm
    1.72
     Bhagavato
    1.71
     Ο
    1.67
    ➣
    1.67
    Escolh
    1.66
     Wills
    1.64
    POSITIVE LOGITS
     jang
    1.52
     theater
    1.51
     juga
    1.48
    .
    1.47
     yang
    1.46
     auch
    1.42
     also
    1.41
     anche
    1.40
     ay
    1.35
     dritte
    1.32
    Activations Density 0.136%

    No Known Activations