© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 4961
    Prev
    Next
    INDEX
    Explanations

    usually, generally, called

    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
     Kam
    0.38
    𝚅
    0.37
     Carmel
    0.36
     jaan
    0.35
     dür
    0.35
     Liam
    0.35
     turístico
    0.35
     করিনি
    0.35
    𝐏
    0.35
     করেছি
    0.34
    POSITIVE LOGITS
    usually
    0.64
     usually
    0.63
    と呼ばれる
    0.60
     généralement
    0.58
    被称为
    0.57
     generalmente
    0.56
     Usually
    0.53
    称为
    0.50
    called
    0.49
     tzw
    0.49
    Activations Density 0.337%

    No Known Activations