© 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. 93221
    Prev
    Next
    INDEX
    Explanations

    collection, collecting, collectors

    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
    AL
    -1.10
    </h1>
    -1.05
    O
    -1.03
    b
    -0.98
    ER
    -0.98
    question
    -0.98
     reduced
    -0.97
     -
    -0.96
     allowed
    -0.96
     etik
    -0.95
    POSITIVE LOGITS
    getCollection
    1.34
    ibouti
    1.29
     collection
    1.29
    neurs
    1.26
    
    1.25
     collectors
    1.24
     колек
    1.23
    coleccion
    1.20
    
    1.20
     collect
    1.20
    Activations Density 0.038%

    No Known Activations