© 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. 102140
    Prev
    Next
    INDEX
    Explanations

    safety and specific locations

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

    expressions of empathy

    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
     పరిస్థ
    0.53
    বাড়ি
    0.49
    䔬
    0.49
    кономи
    0.49
    憔
    0.48
    데이터
    0.48
    来到了
    0.48
     ছবিটি
    0.47
     জায়গা
    0.47
     বাড়ি
    0.46
    POSITIVE LOGITS
     lors
    0.58
    !)
    0.57
    )
    0.52
    );
    0.52
     )
    0.51
    !}
    0.51
    .)
    0.48
    :,
    0.48
     SGD
    0.48
    ),
    0.47
    Activations Density 0.002%

    No Known Activations