© 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. 14768
    Prev
    Next
    INDEX
    Explanations

    butter

    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
     viewpoint
    2.57
    拉克
    2.54
    পালা
    2.44
    ድግዳ
    2.42
    Elev
    2.40
    нят
    2.39
    𝚐
    2.37
    nomina
    2.34
    𝚞
    2.32
    𝚗
    2.31
    POSITIVE LOGITS
    ದಲು
    2.88
    i
    2.86
     brute
    2.67
    ỡng
    2.65
    eredReader
    2.58
    legged
    2.58
    ه
    2.56
    ㅕ
    2.36
    tter
    2.36
    eber
    2.33
    Activations Density 0.009%

    No Known Activations