© 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. 15-GEMMASCOPE-2-RES-16K
    7. 6574
    Prev
    Next
    INDEX
    Explanations

    German personal pronouns and verbs

    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_15_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
    }">
    1.13
    }'.
    1.07
     brengen
    1.05
    }')
    1.04
    тын
    1.03
     خارجية
    1.01
     kara
    1.01
    Quieres
    1.00
    statusBar
    0.98
    ']>
    0.98
    POSITIVE LOGITS
     infatti
    2.50
     pertanto
    2.36
     oftentimes
    2.30
     البته
    2.17
     consequently
    2.16
     understandably
    2.11
     henceforth
    2.11
     generalmente
    2.09
     Normally
    2.09
    Normally
    2.07
    Activations Density 0.011%

    No Known Activations