© 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. 10-GEMMASCOPE-RES-131K
    7. 42972
    Prev
    Next
    INDEX
    Explanations

    code, names, or database tasks

    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_10/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
     and
    -4.28
     perpetually
    -2.56
     blatantly
    -2.52
     epitom
    -2.50
     intricacies
    -2.44
    ........
    -2.39
     unrelenting
    -2.36
     multifaceted
    -2.33
     blistering
    -2.31
     supremely
    -2.28
    POSITIVE LOGITS
     verhind
    2.44
    敺
    2.44
     nimmer
    2.44
    originally
    2.42
     externe
    2.41
     technisch
    2.39
    甞
    2.38
    鶫
    2.36
     aussit
    2.36
    generally
    2.36
    Activations Density 0.000%

    No Known Activations