© 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. 219299
    Prev
    Next
    INDEX
    Explanations

    encapsulated TEOS

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

    ideas, inflation, letters, invoice

    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
    ジナ
    0.55
    𝙫
    0.55
     هە
    0.52
    攽
    0.52
     déchir
    0.51
    ੨
    0.50
     Гинд
    0.49
    右手
    0.49
     фина
    0.48
    📫
    0.48
    POSITIVE LOGITS
     sistemi
    0.50
     spacecraft
    0.50
     remote
    0.49
     traveling
    0.46
     versatile
    0.45
     immobile
    0.45
     farming
    0.44
     monitoring
    0.44
     processes
    0.44
     certific
    0.44
    Activations Density 0.002%

    No Known Activations