© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 39876
    Prev
    Next
    INDEX
    Explanations

    technical terms and descriptors

    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_65k_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
     અલ
    0.42
     خ
    0.41
    購入
    0.41
     purchasing
    0.40
     telephony
    0.38
     ஆண்டு
    0.37
    事實
    0.37
    銓
    0.37
    荃灣
    0.37
    動
    0.37
    POSITIVE LOGITS
    nn
    0.40
     waven
    0.40
    jumlah
    0.39
    Lunch
    0.38
     रेशियो
    0.36
    samples
    0.36
    kmeans
    0.35
    ompok
    0.35
    Luck
    0.35
    saturated
    0.35
    Activations Density 0.002%

    No Known Activations