© 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. 11161
    Prev
    Next
    INDEX
    Explanations

    men, women, couples

    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
    ekyll
    -0.90
     Autoren
    -0.90
     that
    -0.88
    之地
    -0.84
    addCriterion
    -0.82
     cunning
    -0.81
     their
    -0.81
    rąg
    -0.80
    huana
    -0.80
     repayment
    -0.80
    POSITIVE LOGITS
    ""}
    1.17
     whereas
    0.98
     and
    0.92
    °;
    0.91
    /$
    0.90
     zahrani
    0.90
     poži
    0.88
     manicura
    0.88
    月中
    0.86
     förra
    0.85
    Activations Density 0.047%

    No Known Activations