© 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. 98214
    Prev
    Next
    INDEX
    Explanations

    terms and copyright notices

    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
    Allez
    -0.87
     judicia
    -0.81
    žin
    -0.79
     blusa
    -0.77
    Ито
    -0.77
     comanda
    -0.76
    ဩ
    -0.75
    Kamera
    -0.74
     Francia
    -0.74
     catég
    -0.74
    POSITIVE LOGITS
     unirse
    0.89
     nonostante
    0.84
    ŚCI
    0.82
     ان
    0.82
    ŚĆ
    0.82
    纹
    0.80
    IUM
    0.79
     който
    0.79
     અ
    0.77
    外的
    0.76
    Activations Density 1.078%

    No Known Activations