© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 83020
    Prev
    Next
    INDEX
    Explanations

    Sometimes situations or facts

    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
     and
    -1.77
    ledad
    -1.34
    swimming
    -1.34
    uminum
    -1.30
    preneurs
    -1.30
    uated
    -1.28
     défis
    -1.27
    rawn
    -1.27
    ificantly
    -1.27
    osaurus
    -1.26
    POSITIVE LOGITS
     it
    3.33
     you
    2.80
     when
    2.63
     people
    2.52
     there
    2.39
     we
    2.22
     they
    2.20
    When
    2.14
    During
    1.89
     during
    1.78
    Activations Density 0.031%

    No Known Activations