© 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. 34-GEMMASCOPE-RES-131K
    7. 25576
    Prev
    Next
    INDEX
    Explanations

    taking or removing objects

    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
    ombus
    -0.87
    attend
    -0.75
    AccessLevel
    -0.74
     inflows
    -0.73
     vomit
    -0.73
    alay
    -0.73
    onski
    -0.71
     mendat
    -0.71
    umna
    -0.71
    escens
    -0.71
    POSITIVE LOGITS
     take
    2.28
    带
    2.25
    帶
    1.93
     carry
    1.91
     carried
    1.91
    take
    1.84
     emporter
    1.84
     takeaway
    1.84
     TAKE
    1.76
    Take
    1.74
    Activations Density 0.044%

    No Known Activations