© 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. 34-GEMMASCOPE-RES-131K
    4. 82501
    Prev
    Next
    INDEX
    Explanations

    look and feel

    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
    mentaire
    -0.89
    žně
    -0.85
    ciamo
    -0.83
     identifiés
    -0.82
     hierdie
    -0.82
    viser
    -0.82
    猗
    -0.81
    ⌃
    -0.80
    みたいに
    -0.80
     sqft
    -0.80
    POSITIVE LOGITS
     feel
    5.13
     vibe
    3.63
    feel
    3.56
     look
    3.42
     feeling
    3.38
    Feel
    3.16
     Feel
    3.09
     feels
    2.94
     FEEL
    2.61
     atmosphere
    2.47
    Activations Density 0.066%

    No Known Activations