© 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. 14781
    Prev
    Next
    INDEX
    Explanations

    special characters and older words

    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
    <<"
    2.51
    resa
    2.37
    اهرين
    2.21
    acionais
    2.21
    ffine
    2.20
    ça
    2.20
    ্প
    2.18
    XXXX
    2.18
    лены
    2.17
    ंध्र
    2.17
    POSITIVE LOGITS
    팽
    2.69
     quizzes
    2.65
    ೋತಿ
    2.65
    ਟਰ
    2.61
    menubar
    2.52
    meny
    2.46
    네
    2.42
    CARD
    2.34
    리그
    2.29
     StatelessWidget
    2.27
    Activations Density 0.001%

    No Known Activations