© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 92375
    Prev
    Next
    INDEX
    Explanations

    store and retrieve

    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
     localStorage
    -0.88
     Gud
    -0.86
     installing
    -0.85
    uParam
    -0.81
    録画
    -0.80
    荷物
    -0.79
     rouge
    -0.77
     glisser
    -0.77
     depositing
    -0.77
     %=
    -0.76
    POSITIVE LOGITS
     retrieval
    1.38
     Retrieval
    1.22
     retrie
    1.13
     recalled
    1.05
     retrieved
    1.05
    Retrieval
    1.04
     accessed
    1.03
    retrie
    1.01
     accessible
    0.98
     recall
    0.98
    Activations Density 0.092%

    No Known Activations