© 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. 190578
    Prev
    Next
    INDEX
    Explanations

    search, filter, or replace

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

    explaining with analogy and scale

    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
    都
    0.53
    ployed
    0.50
    fav
    0.49
    íti
    0.48
    汹
    0.48
    nour
    0.48
    cett
    0.47
    hout
    0.47
    ly
    0.46
    丸
    0.46
    POSITIVE LOGITS
     Необходимо
    0.52
     Compiler
    0.45
     videomuzda
    0.43
     Dalam
    0.43
     Micros
    0.42
     Gossip
    0.42
     Fernando
    0.41
     Adası
    0.41
     Misalnya
    0.40
     Contoh
    0.40
    Activations Density 0.001%

    No Known Activations