© 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. 65929
    Prev
    Next
    INDEX
    Explanations

    narrative and personal experience descriptions

    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
    rscheinlichkeit
    -1.08
    ulae
    -1.00
     обеспечить
    -0.99
    }_{\
    -0.98
    werkt
    -0.97
     here
    -0.96
     RSSSF
    -0.96
    ό
    -0.93
    ar
    -0.93
    
    -0.92
    POSITIVE LOGITS
     in
    1.22
     sedang
    1.14
     or
    1.13
    กำลัง
    1.06
     large
    1.06
     although
    1.05
     будто
    1.02
     нещо
    1.02
    although
    0.99
     unusually
    0.99
    Activations Density 0.017%

    No Known Activations