© 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. 212663
    Prev
    Next
    INDEX
    Explanations

    than asbestosshall in priorwithout priorutilizing priorsmokes prioroccurs priorbody priorflowering April

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

    prevents negative outcomes

    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
     étrang
    0.48
     彩
    0.45
    Anchor
    0.44
     Marine
    0.43
     étr
    0.43
    Bras
    0.42
     Anchor
    0.41
    水中
    0.40
    Strange
    0.40
    Congressional
    0.40
    POSITIVE LOGITS
     morally
    0.57
     воспита
    0.52
     последу
    0.49
    糺
    0.49
     нрав
    0.48
     ხელისუფ
    0.48
     egalitarian
    0.48
     नैतिक
    0.45
     habitually
    0.45
     sahib
    0.45
    Activations Density 0.001%

    No Known Activations