© 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. 80684
    Prev
    Next
    INDEX
    Explanations

    dated website

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

    leucemia

    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
    4
    0.62
    0
    0.57
    //
    0.54
    相关
    0.54
    /**
    0.52
    ut
    0.51
    uram
    0.51
    5
    0.50
    relevant
    0.49
    高级
    0.49
    POSITIVE LOGITS
     ಹೃದಯ
    0.56
     glycoprotein
    0.52
     glucos
    0.52
     Dynkin
    0.52
     Khark
    0.50
     dour
    0.50
     protein
    0.50
     elemental
    0.50
     HomeScreen
    0.50
     Frobenius
    0.49
    Activations Density 0.001%

    No Known Activations