© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 72209
    Prev
    Next
    INDEX
    Explanations

    planting literal and metaphorical things

    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
    Negative Logits
    The
    -1.92
    kệ
    -1.85
    釹
    -1.81
     antemano
    -1.80
    
    -1.80
     данной
    -1.79
     somente
    -1.76
    ⢪
    -1.76
     Keeps
    -1.75
    %%%%%%%%%%%%
    -1.73
    POSITIVE LOGITS
    \
    2.08
    這樣的
    1.98
     planted
    1.97
     also
    1.95
    c
    1.87
     in
    1.85
     amado
    1.78
     at
    1.77
    Planting
    1.77
     –
    1.77
    Activations Density 0.007%

    No Known Activations