© 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. 50665
    Prev
    Next
    INDEX
    Explanations

    small enough, avoid claims, support business

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

    random, about, complex

    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
     моих
    0.45
    愠
    0.44
    ម្ល
    0.41
    äger
    0.41
     armour
    0.40
     जुनून
    0.40
    ާތ
    0.40
    ेट्टी
    0.40
    Dame
    0.40
     stark
    0.39
    POSITIVE LOGITS
     replacing
    0.48
    Collapsed
    0.48
    al
    0.46
     //<
    0.44
     Reset
    0.43
    bubble
    0.43
    ぶ
    0.43
     Swap
    0.43
    复杂的
    0.42
    ]<<"
    0.42
    Activations Density 0.000%

    No Known Activations