© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77094
    Prev
    Next
    INDEX
    Explanations

    theme song

    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
    s
    -1.03
     disregarding
    -0.88
    uu
    -0.86
     intende
    -0.86
    替代
    -0.83
     mümkün
    -0.82
     fling
    -0.82
     inhale
    -0.82
     fumes
    -0.81
     partecipa
    -0.79
    POSITIVE LOGITS
     song
    1.66
     park
    1.62
     parks
    1.55
    parks
    1.48
    park
    1.44
    song
    1.43
    Park
    1.35
     SONG
    1.32
    Song
    1.29
    парк
    1.24
    Activations Density 0.013%

    No Known Activations