© 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. 26075
    Prev
    Next
    INDEX
    Explanations

    family, children, school, life events

    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
    ULU
    -0.99
    ଶ
    -0.98
    зом
    -0.96
    Ops
    -0.96
     Europy
    -0.92
     человеку
    -0.86
     Slavery
    -0.85
    <em>
    -0.85
    Tac
    -0.85
    ́n
    -0.85
    POSITIVE LOGITS
     family
    1.52
     children
    1.30
    family
    1.20
    孩子的
    1.15
    Familien
    1.09
     important
    1.09
     Schluß
    1.09
     minor
    1.05
     major
    1.05
    開店
    1.05
    Activations Density 0.014%

    No Known Activations