© 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-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 128
    Prev
    Next
    INDEX
    Explanations

    dynamics of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_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
    0
    0.35
    5
    0.28
    2
    0.28
    1
    0.27
     cuyos
    0.26
    8
    0.25
    7
    0.25
     invaders
    0.25
     cuyas
    0.25
    9
    0.25
    POSITIVE LOGITS
    และการ
    0.37
    และความ
    0.37
     आणि
    0.32
     giurid
    0.31
     και
    0.30
     juridique
    0.30
     ਅਤੇ
    0.30
     ಮತ್ತು
    0.30
     والت
    0.30
     અને
    0.29
    Activations Density 18.413%

    No Known Activations