© 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. 153584
    Prev
    Next
    INDEX
    Explanations

    startflax seedBritain

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

    sensitive public interest topics

    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
     absorbs
    0.46
     GSE
    0.44
     PCE
    0.43
    府
    0.43
     Eurasia
    0.43
     XXX
    0.42
     integrates
    0.42
     simply
    0.40
     AGE
    0.40
     TAE
    0.40
    POSITIVE LOGITS
     многочис
    0.57
    ј
    0.54
     кандидат
    0.53
    凳
    0.52
    віда
    0.51
     керів
    0.51
     встреча
    0.50
    铿
    0.48
     обучение
    0.48
     коктей
    0.48
    Activations Density 0.000%

    No Known Activations