© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 942
    Prev
    Next
    INDEX
    Explanations

    no, not, nor

    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
     yep
    -1.51
     and
    -1.45
     so
    -1.37
     yes
    -1.35
     Yeah
    -1.30
     Yep
    -1.29
    Yeah
    -1.23
     yup
    -1.22
     Yes
    -1.20
     yeah
    -1.16
    POSITIVE LOGITS
     not
    2.39
     don
    1.40
     नहीं
    1.39
    actually
    1.30
     they
    1.29
     it
    1.27
    🙅
    1.27
    not
    1.23
     nor
    1.23
    nor
    1.23
    Activations Density 0.009%

    No Known Activations