© 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. 82410
    Prev
    Next
    INDEX
    Explanations

    specific nouns and their source

    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
     acquired
    -1.13
     picked
    -1.13
     sabias
    -0.99
     adqui
    -0.98
    领取
    -0.98
     accepting
    -0.94
     adopted
    -0.94
     derived
    -0.93
     picking
    -0.93
     uptake
    -0.93
    POSITIVE LOGITS
     from
    1.83
     into
    1.43
     to
    1.34
     for
    1.27
     away
    1.20
    放到
    1.17
     out
    1.06
     off
    1.00
    clav
    0.94
     and
    0.93
    Activations Density 0.136%

    No Known Activations