© 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. 33297
    Prev
    Next
    INDEX
    Explanations

    challenges and opportunities faced

    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
    ראש
    -0.87
    Influ
    -0.86
     enthou
    -0.84
    onekana
    -0.82
    influenced
    -0.82
    neming
    -0.81
     권
    -0.81
     risques
    -0.81
     جواب
    -0.81
     terce
    -0.79
    POSITIVE LOGITS
     teaching
    1.52
     teaches
    1.49
     teach
    1.39
    反而
    1.38
     strengthen
    1.37
     opportunity
    1.37
     actually
    1.35
    むしろ
    1.32
     forced
    1.26
    かえ
    1.23
    Activations Density 0.038%

    No Known Activations