© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 33296
    Prev
    Next
    INDEX
    Explanations

    potentially omitted

    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
     Frankie
    0.43
    竄
    0.43
     Aprend
    0.42
     Filed
    0.42
     Kobe
    0.42
     Dip
    0.41
     jerseys
    0.41
     Dive
    0.40
     Cole
    0.40
     Serviço
    0.40
    POSITIVE LOGITS
     wooded
    0.54
    الوجی
    0.53
     vati
    0.52
     montagna
    0.51
    薢
    0.49
    راہ
    0.48
     பச
    0.47
     visc
    0.47
    idegg
    0.47
    nout
    0.46
    Activations Density 0.001%

    No Known Activations