© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 77604
    Prev
    Next
    INDEX
    Explanations

    intermittent reinforcement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DS
    0.48
    nance
    0.47
    ado
    0.46
    .
    0.46
    lum
    0.45
     Decre
    0.45
    edes
    0.45
    ello
    0.44
    ring
    0.44
    DM
    0.44
    POSITIVE LOGITS
    Choisissez
    0.49
    ውነተኛ
    0.48
    ємо
    0.47
     mít
    0.47
     naïve
    0.47
    鏄
    0.47
    ಮುಖ
    0.45
     ብዙውን
    0.45
     dénom
    0.45
     benchmarking
    0.44
    Activations Density 0.000%

    No Known Activations