© 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. 212524
    Prev
    Next
    INDEX
    Explanations

    unless you

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

    herramienta poderosa

    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
    髓
    0.45
    缺乏
    0.45
    被迫
    0.45
    unsafe
    0.43
    外出
    0.43
    rentes
    0.43
     లేదా
    0.43
    indexes
    0.42
    docs
    0.42
    梗
    0.41
    POSITIVE LOGITS
     Lanzarote
    0.49
     Magnificent
    0.48
     nomm
    0.47
     salah
    0.46
     Bahrain
    0.46
     Oman
    0.46
     jednym
    0.46
     hany
    0.46
     glow
    0.45
     purnama
    0.45
    Activations Density 0.000%

    No Known Activations