© 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. 16133
    Prev
    Next
    INDEX
    Explanations

    social roles and relationships

    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
     each
    -1.17
    醜
    -1.05
     this
    -1.05
    ícias
    -1.04
     årets
    -1.02
    ansvar
    -1.01
     onsdag
    -1.01
    tividade
    -1.01
     you
    -0.98
    crats
    -0.98
    POSITIVE LOGITS
     already
    1.42
     who
    1.38
     knew
    1.33
     bereits
    1.30
     then
    1.27
     szint
    1.19
     ebenfalls
    1.15
     was
    1.13
    Then
    1.10
     hatte
    1.08
    Activations Density 0.046%

    No Known Activations