© 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. 177203
    Prev
    Next
    INDEX
    Explanations

    World Consumer Rights Day maximum load

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

    specific phrasing/structure

    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
    https
    0.46
    求
    0.45
    或者
    0.44
    蔚
    0.44
    ើង
    0.43
    套
    0.43
    Https
    0.42
    प्रतिनि
    0.42
    aadhar
    0.42
    上
    0.42
    POSITIVE LOGITS
     परिवारों
    0.49
     Dunes
    0.49
     рэгістрацыі
    0.48
     النقطه
    0.46
    credibly
    0.45
     tribulations
    0.45
     mù
    0.45
     artistes
    0.45
     ordinances
    0.44
    killers
    0.44
    Activations Density 0.001%

    No Known Activations