© 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-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 2511
    Prev
    Next
    INDEX
    Explanations

    performing actions and tasks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ৩
    0.89
    ো
    0.84
    ли
    0.79
    et
    0.78
    ai
    0.78
    AA
    0.71
    ccncc
    0.70
    AT
    0.68
    RAT
    0.67
    ﻞ
    0.66
    POSITIVE LOGITS
     searches
    0.76
     effectuer
    0.75
     исследований
    0.75
    ج
    0.72
     Performs
    0.70
    ق
    0.69
     conducted
    0.66
     tests
    0.65
     investigated
    0.64
     procesu
    0.64
    Activations Density 0.168%

    No Known Activations