© 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. 16-GEMMASCOPE-2-RES-262K
    7. 14816
    Prev
    Next
    INDEX
    Explanations

    player code context

    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_16_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
     necessari
    0.68
    ם
    0.68
    жа
    0.62
    ч
    0.60
    LOAD
    0.59
     레
    0.59
    اہر
    0.59
    ності
    0.59
     airfoil
    0.59
    itatif
    0.59
    POSITIVE LOGITS
    ك
    0.70
    不
    0.70
    น
    0.69
    ed
    0.66
    ↵↵
    0.66
    την
    0.65
    tiene
    0.64
    ta
    0.64
    ുടെ
    0.63
    و
    0.63
    Activations Density 0.013%

    No Known Activations