© 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. 48670
    Prev
    Next
    INDEX
    Explanations

    proposed method or approach

    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
    wants
    -1.02
     окружающей
    -0.95
    ubern
    -0.90
    ihnachts
    -0.88
    itares
    -0.85
    Already
    -0.85
     パーツ
    -0.84
    дії
    -0.84
     絵
    -0.82
    ቸ
    -0.80
    POSITIVE LOGITS
     proposed
    5.88
    Proposed
    4.09
    proposed
    3.94
     Proposed
    3.78
     propose
    3.34
     PROPOSED
    3.14
    PROPOSED
    3.09
     suggested
    2.89
     proposing
    2.89
     proposto
    2.84
    Activations Density 0.130%

    No Known Activations