© 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. 40-GEMMASCOPE-2-RES-262K
    7. 33545
    Prev
    Next
    INDEX
    Explanations

    numbers and dimensions

    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_40_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
    বঙ্গের
    0.43
    霝
    0.42
    ৃক
    0.42
    remain
    0.41
     najlepiej
    0.41
    䞍
    0.41
    ngo
    0.41
    yrch
    0.40
    ቝ
    0.40
     করেননি
    0.40
    POSITIVE LOGITS
     quadratic
    0.53
     govor
    0.53
     spoke
    0.51
     Speaks
    0.50
     talk
    0.49
     Talk
    0.48
     quadrat
    0.46
     Especific
    0.45
     speaks
    0.45
     Quadratic
    0.43
    Activations Density 0.000%

    No Known Activations