© 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. 40-GEMMASCOPE-2-RES-262K
    7. 133167
    Prev
    Next
    INDEX
    Explanations

    smaller user base

    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
     inclus
    0.38
    itabbo
    0.38
    CLAS
    0.38
    熠
    0.37
     inclusions
    0.37
    clas
    0.37
    漣
    0.37
     passes
    0.36
     pasa
    0.36
     folds
    0.36
    POSITIVE LOGITS
     Utama
    0.39
    opropyl
    0.39
    anedi
    0.39
    Philippines
    0.38
     एमएन
    0.38
    pciones
    0.35
    ੱ
    0.35
    𝑜
    0.35
     entice
    0.35
    фф
    0.35
    Activations Density 0.000%

    No Known Activations