© 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. 20310
    Prev
    Next
    INDEX
    Explanations

    free shipping on eligible orders

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

    free shipping on orders over

    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
    发送
    0.52
     mailed
    0.49
    召开
    0.48
     send
    0.47
    没
    0.47
     paid
    0.44
     mailing
    0.44
    为
    0.43
    совой
    0.42
    发放
    0.42
    POSITIVE LOGITS
     hegemony
    0.47
     전국
    0.45
     nettement
    0.43
     فلسطین
    0.43
    порта
    0.42
     المناطق
    0.42
     ))}
    0.41
     Convenience
    0.41
     bandeja
    0.41
     півні
    0.40
    Activations Density 0.011%

    No Known Activations