© 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. 13834
    Prev
    Next
    INDEX
    Explanations

    Starting, Special, Material, What, Note, Data, Quote, Score

    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
    eket
    2.61
    मपुर
    2.57
    觴
    2.51
     Posting
    2.41
    subfloat
    2.34
    _[
    2.32
    рях
    2.31
     scriptlevel
    2.28
    .}\
    2.26
    쏜
    2.24
    POSITIVE LOGITS
    ouring
    3.05
    اب
    2.70
    torn
    2.65
     degenerate
    2.61
    ment
    2.56
    ात
    2.55
    acido
    2.53
    त
    2.48
    azität
    2.47
    使命
    2.47
    Activations Density 0.003%

    No Known Activations