© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 43182
    Prev
    Next
    INDEX
    Explanations

    forced further, forget expensive

    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
     wodurch
    0.59
     Entfer
    0.57
     pavattati
    0.52
    𒋼
    0.52
     waardoor
    0.50
     erset
    0.50
     modificaciones
    0.50
     ombil
    0.50
    زالة
    0.49
     Während
    0.49
    POSITIVE LOGITS
    '
    0.52
    age
    0.48
    mo
    0.48
    ue
    0.48
    Time
    0.47
    yl
    0.47
    {
    0.46
    out
    0.46
    ague
    0.45
    始
    0.45
    Activations Density 0.002%

    No Known Activations