© 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. 102773
    Prev
    Next
    INDEX
    Explanations

    setting properties with methods

    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
     célè
    -1.92
     plafon
    -1.87
     améli
    -1.76
     murales
    -1.64
     télécharge
    -1.63
     花纹
    -1.63
    ほとん
    -1.60
     både
    -1.59
     pittores
    -1.58
    裥
    -1.58
    POSITIVE LOGITS
    n
    1.82
    L
    1.79
     T
    1.79
     Y
    1.78
    u
    1.78
    E
    1.77
     D
    1.73
    D
    1.73
    t
    1.72
    T
    1.71
    Activations Density 0.023%

    No Known Activations