© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 58479
    Prev
    Next
    INDEX
    Explanations

    crystals and stones

    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
     nostalgic
    -0.88
     パール
    -0.83
     nostalgia
    -0.83
    ֠
    -0.82
    !="")
    -0.82
     கொ
    -0.81
     Xtreme
    -0.80
    bertura
    -0.80
     établissement
    -0.79
    讐
    -0.79
    POSITIVE LOGITS
     crystals
    1.73
     crystal
    1.59
     healing
    1.45
     Reiki
    1.37
     stones
    1.29
     Healing
    1.26
    crystal
    1.23
    Crystal
    1.20
     Crystal
    1.19
     quartz
    1.19
    Activations Density 0.012%

    No Known Activations