© 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. 84040
    Prev
    Next
    INDEX
    Explanations

    having trouble or problem

    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
     other
    -1.91
     even
    -1.73
     then
    -1.55
     another
    -1.45
     others
    -1.39
     afterwards
    -1.32
     better
    -1.32
     those
    -1.30
     later
    -1.28
     further
    -1.27
    POSITIVE LOGITS
    のですが
    1.19
     очень
    1.16
     примерно
    1.16
     довольно
    1.16
    なのですが
    1.14
    がとても
    1.13
     octobre
    1.10
     Bardzo
    1.10
     yaklaşık
    1.10
     ziemlich
    1.09
    Activations Density 0.657%

    No Known Activations