© 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. 186179
    Prev
    Next
    INDEX
    Explanations

    travel reviews

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

    typical use scenarios and potential

    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
     Nama
    0.46
    ۔
    0.44
    íta
    0.44
    ಪಿ
    0.44
     दिग्गज
    0.43
    ***************
    0.42
     pita
    0.42
     slain
    0.42
    パーカー
    0.41
     sàng
    0.41
    POSITIVE LOGITS
    leştir
    0.46
    鰭
    0.44
     Л
    0.43
    калә
    0.42
    UIKit
    0.42
     திரு
    0.42
     инфек
    0.41
    setLocation
    0.41
     Raffle
    0.40
    grip
    0.40
    Activations Density 0.000%

    No Known Activations