© 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. 33081
    Prev
    Next
    INDEX
    Explanations

    hope you or things

    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
     bagaimana
    -1.16
     них
    -1.11
     dlatego
    -1.09
     dlaczego
    -1.05
     ponieważ
    -1.04
    izedBox
    -1.04
    astify
    -1.04
    Зміст
    -1.04
    迄
    -1.02
    烩
    -1.02
    POSITIVE LOGITS
     they
    2.41
     that
    2.11
     you
    2.03
     this
    2.03
     we
    2.00
     it
    1.89
     to
    1.76
     there
    1.57
     my
    1.40
     your
    1.36
    Activations Density 0.014%

    No Known Activations