© 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. 99305
    Prev
    Next
    INDEX
    Explanations

    invited to an event

    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
     approving
    -1.05
     agreeing
    -1.01
     officio
    -1.00
    ﾞ
    -0.94
    bių
    -0.91
    门口
    -0.90
    お店の
    -0.85
     победы
    -0.85
    arrivée
    -0.85
     przypadku
    -0.85
    POSITIVE LOGITS
     to
    2.34
     into
    2.16
     onto
    1.34
     participate
    1.20
     guests
    1.13
     participation
    1.10
     diskusi
    0.98
    into
    0.98
     invitation
    0.98
     mukaan
    0.96
    Activations Density 0.011%

    No Known Activations