© 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. 13855
    Prev
    Next
    INDEX
    Explanations

    physically handcrafted luxury items

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

    unique comparison points

    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
    𝗪
    0.54
    𝘄
    0.49
    が付
    0.47
    effectiveness
    0.46
    全体の
    0.46
    𝘀
    0.45
    𝐯
    0.45
    有意
    0.45
     додат
    0.44
    themed
    0.44
    POSITIVE LOGITS
    ]
    0.46
     podrán
    0.45
     Database
    0.45
     Physical
    0.45
     phys
    0.44
     Espagne
    0.44
     Acquire
    0.44
     später
    0.44
     Don
    0.44
     Pued
    0.43
    Activations Density 0.000%

    No Known Activations