© 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. 52445
    Prev
    Next
    INDEX
    Explanations

    performance despite

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

    advantage, higher data

    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
    夫婦
    0.48
     kostenlos
    0.47
    öff
    0.46
    美品
    0.45
    ಯೇ
    0.43
    併
    0.43
    無料
    0.42
     resusc
    0.42
    daniel
    0.41
     Бі
    0.41
    POSITIVE LOGITS
     напо
    0.43
     exce
    0.41
     ...)
    0.41
     rell
    0.41
    °)
    0.40
     peculi
    0.40
    serverId
    0.40
     ரே
    0.39
    ···
    0.39
     jīn
    0.39
    Activations Density 0.000%

    No Known Activations