© 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. 22-GEMMASCOPE-RES-131K
    7. 72858
    Prev
    Next
    INDEX
    Explanations

    this year, edition, or winter

    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_22/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
     teritor
    -1.02
     ngày
    -0.97
     virtues
    -0.96
    Ḍ
    -0.94
     scenes
    -0.94
     दिन
    -0.93
    Ṛ
    -0.93
     helpt
    -0.92
     days
    -0.92
     jours
    -0.91
    POSITIVE LOGITS
     particular
    1.16
     We
    1.01
     again
    0.98
     we
    0.98
     will
    0.96
    again
    0.96
    पया
    0.95
    entait
    0.95
     unprecedented
    0.95
     Strahl
    0.93
    Activations Density 0.029%

    No Known Activations