© 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. 117339
    Prev
    Next
    INDEX
    Explanations

    Stanford University, scaler

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

    threshold detection

    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
     казни
    0.60
    ।]
    0.48
     ਸੀ
    0.46
    !]
    0.46
     ১৯৮
    0.46
    )([
    0.46
     Solicitors
    0.44
     videomuz
    0.43
     ਜਾਂ
    0.42
    /(
    0.41
    POSITIVE LOGITS
    프로
    0.50
     stan
    0.49
     niewiel
    0.48
    Y
    0.47
    𝚃
    0.47
     Stanford
    0.46
     scaler
    0.46
    乘
    0.46
     lighting
    0.46
     University
    0.45
    Activations Density 0.001%

    No Known Activations