© 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. 316
    Prev
    Next
    INDEX
    Explanations

    copyright, java, code, text

    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
     there
    -1.05
     it
    -1.02
     their
    -0.96
    мерть
    -0.94
     this
    -0.92
     now
    -0.91
     gives
    -0.88
     whose
    -0.88
    してくれた
    -0.87
    Usually
    -0.86
    POSITIVE LOGITS
     wondrous
    1.06
    回の
    1.02
     insanely
    1.00
     diversos
    0.94
     tremendous
    0.94
     anderer
    0.92
     decidedly
    0.91
     immense
    0.91
    ρώ
    0.90
     gigantic
    0.90
    Activations Density 0.001%

    No Known Activations