© 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. 22-GEMMASCOPE-RES-131K
    4. 13665
    Prev
    Next
    INDEX
    Explanations

    feeling recognized or valued

    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_22/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
     to
    -1.66
     but
    -1.13
     of
    -1.05
    らかに
    -0.96
    Business
    -0.92
    äfts
    -0.88
    park
    -0.88
    intra
    -0.87
     we
    -0.86
     poésie
    -0.85
    POSITIVE LOGITS
     someone
    1.21
     somebody
    1.14
     recognition
    1.13
     validation
    1.09
     Validation
    1.07
    
    0.98
    binaan
    0.98
    validation
    0.97
     ktoś
    0.97
     しま
    0.97
    Activations Density 0.023%

    No Known Activations