© 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. 91964
    Prev
    Next
    INDEX
    Explanations

    rather than alternative

    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
     không
    -1.86
     δεν
    -1.48
     nicht
    -1.45
     ikke
    -1.41
    不仅
    -1.38
     não
    -1.35
     także
    -1.35
     and
    -1.35
     не
    -1.34
     tidak
    -1.30
    POSITIVE LOGITS
     being
    3.03
     having
    2.22
     relying
    2.00
     just
    1.87
     simply
    1.80
    只是
    1.80
     merely
    1.71
     sendo
    1.68
     étant
    1.64
     rely
    1.63
    Activations Density 0.042%

    No Known Activations