© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 6805
    Prev
    Next
    INDEX
    Explanations

    automating tasks and processes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_12_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
     adipisicing
    2.05
    чатки
    2.00
    ionat
    1.94
    ⎦
    1.92
    tosecond
    1.90
    جتما
    1.90
    CAC
    1.90
     Summon
    1.87
     Augen
    1.86
     Nassau
    1.86
    POSITIVE LOGITS
    鴦
    1.57
    imli
    1.36
    osomal
    1.35
    真的
    1.33
    ほん
    1.26
    化した
    1.24
    ocumented
    1.23
    ranton
    1.22
     hInstance
    1.22
    档
    1.21
    Activations Density 0.236%

    No Known Activations