© 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. 22003
    Prev
    Next
    INDEX
    Explanations

    other hand, legal actions, going to

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

    data model definitions

    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
    mailto
    0.35
     eBook
    0.33
     Mercantile
    0.31
    뵌
    0.30
    Dude
    0.29
    꺽
    0.29
     patronage
    0.28
    dude
    0.28
    publisher
    0.28
     एफ
    0.28
    POSITIVE LOGITS
     constantemente
    0.45
     calculations
    0.35
     মহিলার
    0.35
     formada
    0.34
     которая
    0.34
     Thermodynamic
    0.33
    顴
    0.33
     方法
    0.33
    ாதாரண
    0.32
    🦷
    0.32
    Activations Density 0.002%

    No Known Activations