© 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. 6949
    Prev
    Next
    INDEX
    Explanations

    interviews and photographs

    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
    Anyways
    -1.72
     veggies
    -1.47
     Anyways
    -1.39
     folks
    -1.34
    咱
    -1.33
     anyways
    -1.28
     solamente
    -1.27
     еще
    -1.25
     серьез
    -1.21
    啥
    -1.20
    POSITIVE LOGITS
     yesterday
    1.14
     Unesco
    1.04
     cannot
    1.01
     Photograph
    0.98
     although
    0.93
     indor
    0.93
     barato
    0.88
    ただし
    0.85
     Photographs
    0.84
     until
    0.84
    Activations Density 0.039%

    No Known Activations