© 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. 671
    Prev
    Next
    INDEX
    Explanations

    crawl and penalize issues

    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
     es
    2.80
    은
    2.77
    는
    2.74
    یت
    2.56
     dug
    2.47
     thừa
    2.44
    ised
    2.38
    は
    2.35
    et
    2.35
    ete
    2.33
    POSITIVE LOGITS
    geries
    3.55
    gery
    2.68
    cible
    2.68
    ndown
    2.66
     starters
    2.61
    erun
    2.58
    klore
    2.54
    gings
    2.53
    აზ
    2.49
     prejudicial
    2.49
    Activations Density 0.919%

    No Known Activations