© 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. 22-GEMMASCOPE-RES-131K
    7. 65318
    Prev
    Next
    INDEX
    Explanations

    family and friends

    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
    topLeft
    -0.85
    ഇ
    -0.78
    mpz
    -0.77
    щают
    -0.77
    охо
    -0.77
     Universidades
    -0.76
     today
    -0.75
     infinita
    -0.75
    ednesdays
    -0.75
    cimentos
    -0.75
    POSITIVE LOGITS
     family
    1.17
    FAMILY
    1.13
    family
    1.12
     personal
    1.02
     relatives
    1.01
     nepo
    1.01
     preferential
    1.00
     familiares
    0.95
     brother
    0.94
     familial
    0.94
    Activations Density 0.045%

    No Known Activations