© 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. 197149
    Prev
    Next
    INDEX
    Explanations

    husband, children

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

    Leveraging pre-trained models

    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
    もし
    0.47
    Fantasy
    0.46
    侍
    0.45
    aphyl
    0.43
    ্মদ
    0.42
    LV
    0.42
     बैठक
    0.41
    urt
    0.41
    Produced
    0.41
    僚
    0.41
    POSITIVE LOGITS
     pInBuffer
    0.58
     postérieure
    0.54
     <<<
    0.54
    ය
    0.51
     tille
    0.51
     algéb
    0.51
    etric
    0.50
     recicl
    0.49
     اعلام
    0.48
     Yuc
    0.48
    Activations Density 0.001%

    No Known Activations