© 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. 85042
    Prev
    Next
    INDEX
    Explanations

    multiple languages

    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
     evalu
    0.50
     plantes
    0.47
     apprais
    0.46
    tencent
    0.43
    ssss
    0.42
     御
    0.42
    getTable
    0.41
    r
    0.41
    iness
    0.41
     husband
    0.40
    POSITIVE LOGITS
    ٔ
    0.52
    般
    0.43
    Sim
    0.43
    ذا
    0.42
    ٴ
    0.41
    준
    0.41
    ೂ
    0.40
    MyAdmin
    0.39
    bruck
    0.39
    Tel
    0.39
    Activations Density 0.001%

    No Known Activations