© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 22292
    Prev
    Next
    INDEX
    Explanations

    words in technical, legal, or historical contexts

    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_31_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
    ма
    0.65
    ал
    0.59
    יל
    0.57
    kében
    0.57
    Д
    0.57
    ка
    0.56
    语句
    0.56
    יר
    0.55
    КА
    0.55
    리
    0.55
    POSITIVE LOGITS
     regul
    0.58
     dos
    0.57
     V
    0.57
     de
    0.55
     en
    0.54
     los
    0.54
     ل
    0.52
     socios
    0.52
     E
    0.52
     roz
    0.51
    Activations Density 0.222%

    No Known Activations