© 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. 180938
    Prev
    Next
    INDEX
    Explanations

    gasoline, propane, or financing

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

    customize, process, essential instructions

    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
     आढळ
    0.45
    ज
    0.43
     پان
    0.42
    чеб
    0.42
     Coron
    0.41
     داشت
    0.40
     بهره
    0.40
    ریز
    0.40
    引き続き
    0.40
    嵬
    0.40
    POSITIVE LOGITS
    IR
    0.50
    િટ
    0.50
    it
    0.48
    UT
    0.48
     financement
    0.48
     discut
    0.48
     financing
    0.48
    يو
    0.47
    นาน
    0.47
    ný
    0.46
    Activations Density 0.000%

    No Known Activations