© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 119219
    Prev
    Next
    INDEX
    Explanations

    propaganda against

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    covite
    -0.81
    どれも
    -0.75
    LikeLike
    -0.75
     sekitarnya
    -0.75
    輜
    -0.71
    zkę
    -0.71
    اعم
    -0.70
    сут
    -0.69
     nepal
    -0.69
     something
    -0.68
    POSITIVE LOGITS
     slide
    1.00
     slides
    0.93
     Slide
    0.92
    Slide
    0.86
    iexcl
    0.85
    banken
    0.84
    ängen
    0.81
     Slides
    0.81
    ロング
    0.81
    Slides
    0.79
    Activations Density 0.002%

    No Known Activations