© 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. 32459
    Prev
    Next
    INDEX
    Explanations

    life, animation, becoming intelligent

    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
    pickle
    -0.74
     Entreprises
    -0.73
    ッと
    -0.73
    ulence
    -0.72
     Enterprises
    -0.71
     épreuves
    -0.71
    ulian
    -0.71
    țiune
    -0.71
    Moment
    -0.70
    촌
    -0.70
    POSITIVE LOGITS
     sentient
    2.52
     animate
    2.41
     alive
    2.22
    animate
    2.02
     anthrop
    2.00
     inanimate
    1.96
    senti
    1.78
     animated
    1.76
     Animate
    1.62
    alive
    1.60
    Activations Density 0.047%

    No Known Activations