© 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. 48555
    Prev
    Next
    INDEX
    Explanations

    lunar and moon related terms

    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
     AttributeSet
    -0.84
    ributos
    -0.79
     ورود
    -0.77
    seher
    -0.77
    ẩu
    -0.76
    spannung
    -0.76
    ridad
    -0.74
    tacles
    -0.72
     Isabelle
    -0.72
     IFT
    -0.71
    POSITIVE LOGITS
     lunar
    2.02
     Moon
    1.70
     Lunar
    1.63
    lunar
    1.48
    Lunar
    1.45
     moon
    1.39
    Moon
    1.34
     Luna
    1.32
     MOON
    1.26
     月
    1.20
    Activations Density 0.017%

    No Known Activations