© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 2592
    Prev
    Next
    INDEX
    Explanations

    end of code blocks

    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
    assar
    1.83
     FutureWarning
    1.78
     '+'
    1.76
    ܦ
    1.74
    ής
    1.65
     throwIfNotFound
    1.64
     其中
    1.62
    τες
    1.62
     Apart
    1.62
     фундамента
    1.62
    POSITIVE LOGITS
    ت
    2.15
    ing
    1.94
    zerel
    1.44
    eenth
    1.44
    arith
    1.41
    iquement
    1.40
    vious
    1.38
    сет
    1.37
    olol
    1.36
    itiert
    1.36
    Activations Density 0.089%

    No Known Activations