© 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. 86812
    Prev
    Next
    INDEX
    Explanations

    family members and kin

    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
    malink
    -0.91
    ꯡ
    -0.87
    idou
    -0.85
    ✎
    -0.85
     sait
    -0.85
     caliente
    -0.85
     cuya
    -0.84
     genomen
    -0.83
    ворю
    -0.82
    мм
    -0.81
    POSITIVE LOGITS
     several
    1.93
     nieces
    1.77
     many
    1.74
     numerous
    1.68
     also
    1.44
     nephews
    1.43
     여러
    1.38
     niece
    1.26
     plusieurs
    1.23
     nephew
    1.20
    Activations Density 0.001%

    No Known Activations