© 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. 10-GEMMASCOPE-RES-131K
    7. 11690
    Prev
    Next
    INDEX
    Explanations

    abstract concepts and states

    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
     you
    -1.78
     nowy
    -1.62
     of
    -1.53
     part
    -1.52
     faisant
    -1.48
    阻止
    -1.47
     szklan
    -1.45
     nieuwe
    -1.42
    camore
    -1.41
     section
    -1.41
    POSITIVE LOGITS
     only
    1.69
     both
    1.68
     PLANE
    1.67
     this
    1.55
     pouze
    1.48
     dör
    1.45
    gendes
    1.44
     nyeri
    1.37
     when
    1.36
     Probably
    1.34
    Activations Density 0.396%

    No Known Activations