© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48807
    Prev
    Next
    INDEX
    Explanations

    affiliation and group 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_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
    λα
    -0.80
     AMONG
    -0.76
    рма
    -0.76
     Eugenia
    -0.76
     Marissa
    -0.71
    canf
    -0.71
    äum
    -0.69
    akh
    -0.69
    backdrop
    -0.69
    charm
    -0.68
    POSITIVE LOGITS
     affiliation
    4.16
     affiliations
    3.36
    affiliation
    3.05
     membership
    3.05
     Affiliation
    2.77
     belonging
    2.61
     belong
    2.55
     affiliated
    2.53
     принадле
    2.47
    Affiliation
    2.47
    Activations Density 0.068%

    No Known Activations