© 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. 199152
    Prev
    Next
    INDEX
    Explanations

    information boxes

    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
    AN
    0.49
    EventArgs
    0.46
    Yeni
    0.46
    Arg
    0.45
    R
    0.44
    Af
    0.44
    Av
    0.43
    Ev
    0.42
    Ast
    0.42
    Y
    0.41
    POSITIVE LOGITS
    ろん
    0.50
    閉
    0.47
     Deuteronomy
    0.47
    増や
    0.47
    бычно
    0.46
    طع
    0.46
    кратно
    0.45
    それぞれ
    0.45
    مرار
    0.44
     हार्मोन
    0.44
    Activations Density 0.004%

    No Known Activations