© 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. 28074
    Prev
    Next
    INDEX
    Explanations

    books, dye, realistic, published

    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
     extiende
    0.50
     tranquila
    0.48
     scena
    0.45
     provoca
    0.45
     plusieurs
    0.45
     nije
    0.45
     conjunta
    0.45
    話
    0.45
     prioridad
    0.44
     وړاندوینې
    0.44
    POSITIVE LOGITS
    すぎる
    0.42
    uring
    0.41
     همیشه
    0.41
    medskip
    0.40
    ôm
    0.39
    自行
    0.38
    品的
    0.38
    ని
    0.38
    released
    0.37
    worldly
    0.37
    Activations Density 0.004%

    No Known Activations