© 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. 392
    Prev
    Next
    INDEX
    Explanations

    cv:: namespace qualifier

    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
     of
    -0.91
     on
    -0.88
     misleading
    -0.72
     inactive
    -0.71
     removeFrom
    -0.70
    只要
    -0.69
    規制
    -0.69
     infección
    -0.68
     outside
    -0.68
    ᥣ
    -0.68
    POSITIVE LOGITS
     véhic
    0.86
    ções
    0.86
     vitae
    0.84
    ។
    0.84
    pasang
    0.82
    isiaj
    0.82
     SENIOR
    0.82
    ooooooo
    0.82
    чника
    0.82
    čiu
    0.81
    Activations Density 0.005%

    No Known Activations