© 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. 13-GEMMASCOPE-2-RES-16K
    4. 2296
    Prev
    Next
    INDEX
    Explanations

    without needing explicit labels

    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_13_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
     美国
    1.95
     Amerika
    1.86
     США
    1.84
     미국
    1.75
     ২২
    1.74
     ১১
    1.74
     Ρ
    1.73
     ১৮
    1.73
     ২৮
    1.73
     ১৩
    1.71
    POSITIVE LOGITS
    situation
    1.19
    tub
    1.17
    saving
    1.16
    potential
    1.10
    tions
    1.10
    something
    1.07
    tout
    1.07
    tak
    1.04
    écart
    1.04
    具体的な
    1.04
    Activations Density 0.269%

    No Known Activations