© 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. 78106
    Prev
    Next
    INDEX
    Explanations

    beauty and the beast

    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
     IMAP
    -0.80
     Raad
    -0.77
    んですか
    -0.75
     angekommen
    -0.74
     dlg
    -0.73
     planète
    -0.73
    闡
    -0.72
    ো
    -0.72
     verbreitet
    -0.71
     eugen
    -0.71
    POSITIVE LOGITS
     Beauty
    2.13
     Beast
    2.05
    Beauty
    1.90
     beast
    1.71
    Beast
    1.62
     beauty
    1.58
    beast
    1.55
     Belle
    1.48
    beauty
    1.43
     BEAUTY
    1.42
    Activations Density 0.018%

    No Known Activations