© 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. 13-GEMMASCOPE-2-RES-16K
    7. 2045
    Prev
    Next
    INDEX
    Explanations

    observing states and actions

    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
    yı
    1.33
    σκευ
    1.31
    ר
    1.21
     Meat
    1.19
    Meat
    1.19
    ubs
    1.18
    spf
    1.18
    ConformanceMode
    1.17
    Specs
    1.17
    ែក
    1.15
    POSITIVE LOGITS
     깊
    1.21
    振動
    1.18
     stillness
    1.16
     восприя
    1.09
     움
    1.09
     arrhythmia
    1.08
     restless
    1.06
     contemplation
    1.06
     moments
    1.05
     глубо
    1.04
    Activations Density 0.000%

    No Known Activations