© 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. 708
    Prev
    Next
    INDEX
    Explanations

    Roth IRA, Fibonacci, Bernoulli

    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
    y
    2.30
    ed
    2.27
    ndrome
    1.98
    edk
    1.89
    ة
    1.82
    ыр
    1.81
    ان
    1.80
    en
    1.77
    ো
    1.76
    emn
    1.74
    POSITIVE LOGITS
    $\
    2.51
    𝓷
    2.34
     \]
    2.28
    ッピー
    2.23
     \*
    2.18
     ưa
    2.14
    。\
    2.11
     \[
    2.09
    经纪
    2.08
     performing
    2.06
    Activations Density 0.048%

    No Known Activations