© 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. 84425
    Prev
    Next
    INDEX
    Explanations

    policies and roles

    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
    grazie
    -0.80
     skå
    -0.76
    ượng
    -0.71
     Locale
    -0.69
     canv
    -0.69
     maintien
    -0.68
     Breit
    -0.66
    achelors
    -0.66
    komendasi
    -0.66
    Href
    -0.66
    POSITIVE LOGITS
     policy
    1.56
     policies
    1.35
    policy
    1.34
     Policy
    1.30
    policies
    1.23
    Policy
    1.23
     Policies
    1.22
    POLICY
    1.20
     POLICY
    1.13
    Policies
    1.12
    Activations Density 0.033%

    No Known Activations