© 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. 83402
    Prev
    Next
    INDEX
    Explanations

    advocacy and advocacy groups

    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
    ينما
    -0.95
     geringen
    -0.90
    re
    -0.87
    Creators
    -0.85
     eminent
    -0.85
     Aussch
    -0.84
     secretario
    -0.83
    ものに
    -0.83
     günstiger
    -0.82
     oh
    -0.82
    POSITIVE LOGITS
    advoc
    1.20
     groups
    1.19
    Advocate
    1.16
     Advocates
    1.14
     advoc
    1.13
     Advocate
    1.11
    voc
    1.08
     advocate
    1.03
     Advoc
    1.01
     advocacy
    1.01
    Activations Density 0.012%

    No Known Activations