© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 83790
    Prev
    Next
    INDEX
    Explanations

    comparisons or alternatives

    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
     ciertas
    -1.38
     cierta
    -1.27
     ciertos
    -1.20
    wiſe
    -1.13
     추가
    -1.09
     bepaalde
    -1.08
     довольно
    -1.08
    Certain
    -1.05
    unusual
    -1.05
     cierto
    -1.05
    POSITIVE LOGITS
     better
    3.88
     more
    2.67
    better
    2.64
     another
    2.55
     safer
    2.50
     nicer
    2.31
     stronger
    2.30
     healthier
    2.23
     easier
    2.20
    更好的
    2.20
    Activations Density 0.108%

    No Known Activations