© 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. 36545
    Prev
    Next
    INDEX
    Explanations

    language of, all stores, wiring harness

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

    increased efficiency and innovation

    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
    apayati
    0.48
    angulo
    0.48
    elar
    0.44
     fondness
    0.43
    ята
    0.43
     пройдет
    0.43
    rians
    0.42
     뭔
    0.42
    binding
    0.42
    ‍या
    0.42
    POSITIVE LOGITS
     Hg
    0.51
     PARTIC
    0.49
                    
    0.46
     Initialize
    0.46
     Configure
    0.46
     Register
    0.46
    Maggie
    0.46
     configure
    0.46
     IPs
    0.46
     Hurry
    0.46
    Activations Density 0.000%

    No Known Activations