© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 5005
    Prev
    Next
    INDEX
    Explanations

    technical terms or features

    np_acts-logits-general · gemini-2.5-flash-lite

    code and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ഇത
    0.32
    বড়
    0.30
     неё
    0.30
     बर्खास्त
    0.30
     मौका
    0.29
    こちらの
    0.29
     કરવાની
    0.29
    𝚢
    0.29
    പ്പോൾ
    0.29
     करंट
    0.29
    POSITIVE LOGITS
     that
    0.42
     with
    0.42
    with
    0.42
     consisting
    0.41
     featuring
    0.41
     עם
    0.40
    that
    0.38
     which
    0.38
     of
    0.37
     waarmee
    0.35
    Activations Density 0.472%

    No Known Activations