© 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. 110156
    Prev
    Next
    INDEX
    Explanations

    iOS

    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
    c
    0.69
    o
    0.67
    ся
    0.59
    n
    0.59
    u
    0.58
    ohid
    0.57
    an
    0.56
     trotzdem
    0.55
    man
    0.55
    oh
    0.55
    POSITIVE LOGITS
     πίνα
    0.63
     reeds
    0.62
    舢
    0.57
    herent
    0.56
     պ
    0.56
     промышлен
    0.56
     caldera
    0.55
     crimes
    0.55
    者に
    0.55
    저
    0.54
    Activations Density 0.002%

    No Known Activations