© 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. 149679
    Prev
    Next
    INDEX
    Explanations

    misunderstood, publish, known

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

    discernment to knowledge

    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
    ROCK
    0.42
     nField
    0.42
     rd
    0.42
    INavigation
    0.41
    )
    0.40
     keny
    0.40
    rutt
    0.39
     tru
    0.39
    WriteLine
    0.39
    чка
    0.39
    POSITIVE LOGITS
     Первая
    0.57
    acionais
    0.51
    ansı
    0.50
    Como
    0.50
     ಗು
    0.50
     caratteristiche
    0.50
     विमा
    0.49
    MDEwOlJlcG
    0.49
     características
    0.49
    𒁹
    0.49
    Activations Density 0.000%

    No Known Activations