© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 10938
    Prev
    Next
    INDEX
    Explanations

    on social media

    np_acts-logits-general · gemini-2.5-flash-lite

    Borussia Dortmund asteroid

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
     resettlement
    0.51
     electrónico
    0.45
     uploading
    0.45
    🆙
    0.44
     orbital
    0.43
     roving
    0.43
    飜
    0.43
     behöver
    0.43
    burner
    0.43
     अपलोड
    0.42
    POSITIVE LOGITS
    </em>
    0.51
    ેશ
    0.50
    '):
    0.46
     SmackDown
    0.46
    меется
    0.44
    ющих
    0.44
    ள்ளனர்
    0.43
    тивного
    0.42
    тивно
    0.42
     કહ્યું
    0.42
    Activations Density 0.000%

    No Known Activations