© 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. 7-GEMMASCOPE-2-RES-16K
    7. 13407
    Prev
    Next
    INDEX
    Explanations

    Save the code

    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
     wa
    1.66
     deem
    1.66
     perceives
    1.65
     situations
    1.65
     allows
    1.62
     을
    1.61
    람
    1.58
     actually
    1.57
    ↵↵
    1.57
     テ
    1.55
    POSITIVE LOGITS
    一股
    1.89
    बरा
    1.72
    Achievements
    1.71
     publicit
    1.67
     fratello
    1.67
     ఆదాయ
    1.66
    一副
    1.65
     traducción
    1.64
     কতক
    1.64
    Precio
    1.63
    Activations Density 0.120%

    No Known Activations