© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 50412
    Prev
    Next
    INDEX
    Explanations

    Map features, bibliography entries, videos

    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
     slaughter
    -0.75
    Noc
    -0.72
     wheelchairs
    -0.70
    プター
    -0.69
    ilée
    -0.68
     électriques
    -0.66
     cemeteries
    -0.66
     defences
    -0.66
     Mississauga
    -0.66
    wives
    -0.65
    POSITIVE LOGITS
    deserved
    0.66
    ᠬ
    0.65
     endure
    0.65
    LayoutStyle
    0.64
     down
    0.63
    cripted
    0.62
    broad
    0.61
    ERSON
    0.60
    attn
    0.60
     viên
    0.60
    Activations Density 0.055%

    No Known Activations