© 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. 76950
    Prev
    Next
    INDEX
    Explanations

    documentation alias

    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
     if
    -1.11
     only
    -0.89
     While
    -0.88
     featuring
    -0.87
     Trying
    -0.84
     Usually
    -0.83
    𝘳
    -0.83
     with
    -0.83
    getFrom
    -0.83
    soldiers
    -0.82
    POSITIVE LOGITS
     российской
    1.00
     dismal
    1.00
     momentous
    0.96
     magnificent
    0.94
     comical
    0.91
     marvelous
    0.87
    approximately
    0.87
     monstrous
    0.86
     horrible
    0.86
     captivating
    0.86
    Activations Density 0.005%

    No Known Activations