© 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. 63216
    Prev
    Next
    INDEX
    Explanations

    handsome male protagonists

    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
     timid
    -0.86
     giggled
    -0.83
    skine
    -0.79
     shri
    -0.79
     トリ
    -0.78
    plaats
    -0.78
     trembling
    -0.77
    small
    -0.76
     cheery
    -0.74
     bright
    -0.73
    POSITIVE LOGITS
     handsome
    1.38
    handsome
    1.24
     Handsome
    1.02
    Handsome
    1.00
     CEO
    0.94
    businessman
    0.90
    Sexy
    0.85
     tall
    0.84
     masculine
    0.84
     possessive
    0.84
    Activations Density 0.013%

    No Known Activations