© 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. 97708
    Prev
    Next
    INDEX
    Explanations

    highest class, your needs

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

    list modification or compiler 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
    น
    0.50
    ใน
    0.49
     bea
    0.48
    res
    0.46
     in
    0.45
    OR
    0.42
    tailwind
    0.42
    ñada
    0.42
    done
    0.42
     있으면
    0.42
    POSITIVE LOGITS
     മത്സ്യ
    0.49
    經常
    0.48
     Heer
    0.48
     রহস্য
    0.46
    птовалю
    0.45
    𝗧
    0.45
     islets
    0.44
     contemporaries
    0.43
     ске
    0.43
     ఇది
    0.43
    Activations Density 0.001%

    No Known Activations