© 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. 184550
    Prev
    Next
    INDEX
    Explanations

    Airport Extreme, allergens, carry, enforcement

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

    common, necessary, or likely aspects

    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
    LayoutStyle
    0.48
    ংস
    0.46
    北部
    0.46
    䐝
    0.44
    Builders
    0.44
    LayerView
    0.44
     καρ
    0.43
    킬
    0.43
    續
    0.43
    बि
    0.42
    POSITIVE LOGITS
    s
    0.49
     dispon
    0.47
    a
    0.47
     backtracking
    0.46
     desconoc
    0.46
    trivial
    0.46
     sistemi
    0.45
     pie
    0.45
    upon
    0.45
     leggi
    0.45
    Activations Density 0.001%

    No Known Activations