© 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. 93956
    Prev
    Next
    INDEX
    Explanations

    boost and c++ headers

    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
    gak
    -0.75
     pylint
    -0.74
     भाग
    -0.67
    럽
    -0.67
    ภาย
    -0.66
     gelungen
    -0.64
     gezwungen
    -0.63
    )._
    -0.63
     fört
    -0.62
     hostility
    -0.61
    POSITIVE LOGITS
     boost
    1.75
    boost
    1.53
     boosting
    1.40
     boosts
    1.34
     BOOST
    1.26
    Boost
    1.20
     Boost
    1.17
    BOOST
    1.16
     boosted
    1.10
     Poco
    1.08
    Activations Density 0.108%

    No Known Activations