© 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. 169654
    Prev
    Next
    INDEX
    Explanations

    workshop on, photography and, end, small and, either at

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

    leading to uncertainty or risk

    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
    砚
    0.54
    ()},
    0.46
     нередко
    0.44
     elucidated
    0.44
    ),
    0.43
    ାର
    0.42
    ([]);
    0.41
     []),
    0.41
    িন্ন
    0.41
     сорта
    0.41
    POSITIVE LOGITS
    u
    0.49
     takeover
    0.46
     Serena
    0.46
     הח
    0.45
     Ingers
    0.44
     loudest
    0.44
    ational
    0.44
    very
    0.43
    掫
    0.43
     fastest
    0.43
    Activations Density 0.000%

    No Known Activations