© 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. 15479
    Prev
    Next
    INDEX
    Explanations

    trust, behaviour, intentions

    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
     粥
    -0.93
     legitimacy
    -0.91
    FontAwesome
    -0.91
    řes
    -0.90
     tuong
    -0.89
     idiota
    -0.88
     ambayo
    -0.87
     allmän
    -0.86
     heureuse
    -0.85
     amorosa
    -0.85
    POSITIVE LOGITS
     their
    1.28
     will
    1.16
     intentions
    1.12
     they
    1.12
     leopard
    0.91
     ihrer
    0.91
     leop
    0.88
     Brésil
    0.85
     stone
    0.81
     would
    0.81
    Activations Density 0.043%

    No Known Activations