© 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. 180623
    Prev
    Next
    INDEX
    Explanations

    workers, possible, abundant, details

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

    generator inverter older

    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
     cittam
    0.54
    РА
    0.52
     patrocin
    0.52
     frequented
    0.47
     техні
    0.46
    🐦
    0.46
     техни
    0.46
    もある
    0.46
     дву
    0.46
    б
    0.46
    POSITIVE LOGITS
    Interfaces
    0.52
    lN
    0.51
     Interfaces
    0.48
    tsc
    0.48
     આનંદ
    0.48
    encoders
    0.47
    ضاف
    0.47
     Oscillator
    0.47
    kul
    0.45
    katan
    0.45
    Activations Density 0.000%

    No Known Activations