© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 84972
    Prev
    Next
    INDEX
    Explanations

    emotions and states of mind

    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_10/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
     будут
    -1.47
     entonces
    -1.42
     wtedy
    -1.40
     organisiert
    -1.37
     selben
    -1.35
     vermutlich
    -1.34
     verstanden
    -1.33
     ascer
    -1.30
     erlä
    -1.29
     Then
    -1.27
    POSITIVE LOGITS
     and
    1.74
    7
    1.58
    </u>
    1.48
    8
    1.48
    9
    1.47
    1
    1.43
    
    1.40
    6
    1.38
    :^
    1.38
    </h4>
    1.36
    Activations Density 0.062%

    No Known Activations