© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30299
    Prev
    Next
    INDEX
    Explanations

    Samsung Galaxy

    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
    CardView
    -0.78
     tslint
    -0.77
     faccia
    -0.76
    addData
    -0.76
    saber
    -0.72
    จุด
    -0.70
     bambino
    -0.70
     TRANSL
    -0.69
     flesta
    -0.68
     elongated
    -0.68
    POSITIVE LOGITS
     Galaxy
    1.17
    Samsung
    1.00
     Samsung
    0.98
    Galaxy
    0.81
     BTC
    0.77
     vacu
    0.77
    Bes
    0.77
     Rats
    0.76
    க்க
    0.75
     سامسونگ
    0.75
    Activations Density 0.005%

    No Known Activations