© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49476
    Prev
    Next
    INDEX
    Explanations

    opening negotiations

    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
    昆布
    -0.80
    hésite
    -0.76
     gardener
    -0.71
    ]=$
    -0.70
    arken
    -0.69
    シャンプー
    -0.69
    ihe
    -0.69
    Edmonton
    -0.68
    гры
    -0.68
    otal
    -0.67
    POSITIVE LOGITS
     creation
    0.91
    dji
    0.81
     hardened
    0.81
     cheap
    0.79
     Knapp
    0.79
    మూ
    0.79
    رات
    0.77
     whitespace
    0.76
    create
    0.75
     Create
    0.75
    Activations Density 0.011%

    No Known Activations