© 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. 13-GEMMASCOPE-2-RES-16K
    7. 4831
    Prev
    Next
    INDEX
    Explanations

    numbered list separators

    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
     þe
    1.52
    barui
    1.49
     hỏi
    1.49
    ião
    1.45
    bodied
    1.36
    ί
    1.36
    pping
    1.34
     vén
    1.33
     preguntó
    1.30
    <unused1968>
    1.29
    POSITIVE LOGITS
    行业
    1.15
    =’
    1.12
    ols
    1.10
     Major
    1.10
    روت
    1.07
     Growth
    1.06
     صعبه
    1.05
    сад
    1.03
     sind
    1.02
     Override
    1.02
    Activations Density 0.000%

    No Known Activations