© 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. 184085
    Prev
    Next
    INDEX
    Explanations

    specific keywords

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

    Pi to decimal places

    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
     る
    0.50
    essayer
    0.48
     teorías
    0.47
    ToJava
    0.47
     profondeur
    0.46
    亰
    0.46
    渟
    0.46
     व्यायाम
    0.45
    ஜீ
    0.45
    माजिक
    0.45
    POSITIVE LOGITS
    fashion
    0.55
    j
    0.55
    ↵
    0.55
    new
    0.53
    my
    0.51
    no
    0.50
    lin
    0.50
    model
    0.49
    nyc
    0.48
    ↵↵
    0.48
    Activations Density 0.001%

    No Known Activations