© 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. 22-GEMMASCOPE-RES-131K
    7. 79836
    Prev
    Next
    INDEX
    Explanations

    membership

    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_22/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
     geliefert
    -1.20
    alder
    -1.11
    ราคา
    -1.11
     Jahrhundert
    -1.06
    monių
    -1.04
    assigned
    -1.04
     probable
    -1.04
    🚤
    -1.03
     dicendo
    -1.03
     看
    -1.02
    POSITIVE LOGITS
     membership
    1.96
     its
    1.63
     线条
    1.37
     memberships
    1.30
     members
    1.29
     monthly
    1.22
    membership
    1.17
     quarterly
    1.16
     边框
    1.15
     member
    1.09
    Activations Density 0.052%

    No Known Activations