© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 80780
    Prev
    Next
    INDEX
    Explanations

    kit will

    np_acts-logits-general · gemini-2.5-flash-lite

    being tracked

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Businesses
    0.47
     Sequencing
    0.45
     Automation
    0.44
    髑
    0.44
    http
    0.41
     Completion
    0.41
     Reasoning
    0.41
    剛
    0.41
     Effective
    0.41
    RIG
    0.41
    POSITIVE LOGITS
    weiss
    0.55
     गुलाबी
    0.52
    absch
    0.51
    katore
    0.50
    នៃការ
    0.49
    kennung
    0.48
     empate
    0.47
     belieb
    0.47
     площади
    0.46
     veinte
    0.46
    Activations Density 0.004%

    No Known Activations