© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 4838
    Prev
    Next
    INDEX
    Explanations

    suggestions after 'consider'

    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
    عه
    2.32
    یان
    2.28
    esian
    2.22
     tesam
    2.16
    ্ম্ম
    2.15
    ે
    2.04
    چھا
    2.04
    ام
    2.04
    писи
    2.02
    oš
    2.02
    POSITIVE LOGITS
     determinante
    2.35
    蒻
    2.29
    Issues
    2.28
    +#+#
    2.25
    蟀
    2.21
     perdere
    2.16
    Surprisingly
    2.14
    सेवी
    2.14
     pinch
    2.12
    躇
    2.10
    Activations Density 0.217%

    No Known Activations