© 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. 81553
    Prev
    Next
    INDEX
    Explanations

    as far as I can

    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
     probably
    -1.10
     cocok
    -0.91
     EPISODE
    -0.88
     lecteur
    -0.85
     костюм
    -0.85
    probably
    -0.85
     potentially
    -0.85
    netje
    -0.84
     probable
    -0.84
     обуви
    -0.84
    POSITIVE LOGITS
     see
    1.27
     can
    1.11
     recall
    1.03
    see
    1.03
     recollect
    0.96
     understanding
    0.94
     understands
    0.93
    知る
    0.92
     research
    0.90
     gather
    0.90
    Activations Density 0.037%

    No Known Activations