© 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-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 6578
    Prev
    Next
    INDEX
    Explanations

    word endings like -ing, -ive, -al

    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
     руха
    2.14
     ozn
    1.92
    жды
    1.90
     pomiędzy
    1.90
     dni
    1.90
     мнению
    1.89
     danni
    1.89
    辈
    1.88
     чином
    1.88
    рованной
    1.87
    POSITIVE LOGITS
    érique
    1.89
    ћин
    1.81
     Sensing
    1.79
    ünstler
    1.79
    jakarta
    1.75
    酎
    1.71
    eway
    1.68
     CXCR
    1.66
    ewell
    1.64
    ắ
    1.59
    Activations Density 0.317%

    No Known Activations