© 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. 33814
    Prev
    Next
    INDEX
    Explanations

    crisis, shelter, violence, support

    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
    儉
    -0.79
     praça
    -0.77
    烹
    -0.75
    ₱
    -0.72
    вня
    -0.69
     ブランド
    -0.69
     neighborhood
    -0.69
     animal
    -0.69
    挙げ
    -0.68
    Fade
    -0.67
    POSITIVE LOGITS
     Rough
    1.16
     rough
    1.12
    rough
    1.02
    Accommodation
    0.91
    Rough
    0.90
     accommodation
    0.86
    support
    0.85
    recursion
    0.84
     entrenched
    0.82
    recursive
    0.81
    Activations Density 0.019%

    No Known Activations