© 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. 131293
    Prev
    Next
    INDEX
    Explanations

    wage law

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

    relative to

    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
    ENAME
    0.57
    Sheep
    0.47
    Lamp
    0.47
    А
    0.46
    Ρ
    0.45
    Lighting
    0.45
    Env
    0.44
     wasn
    0.43
    нет
    0.42
    っては
    0.42
    POSITIVE LOGITS
    idad
    0.51
     Token
    0.46
     originales
    0.45
     MetaMask
    0.45
     Szym
    0.44
    悱
    0.43
     boundaries
    0.43
     columnalign
    0.43
     homeostasis
    0.43
    verters
    0.42
    Activations Density 0.002%

    No Known Activations