© 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. 16-GEMMASCOPE-2-RES-262K
    4. 18324
    Prev
    Next
    INDEX
    Explanations

    how well do

    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
    K
    0.63
    نی
    0.61
    nombre
    0.61
    Nombre
    0.61
    ۳
    0.60
     italien
    0.58
    Massage
    0.58
    (":")[
    0.58
    azione
    0.57
    ణం
    0.56
    POSITIVE LOGITS
    น
    0.69
    यद
    0.65
     dough
    0.57
    ংকর
    0.56
     συ
    0.55
     ability
    0.55
     deterioration
    0.54
     Dough
    0.54
     vur
    0.52
    奀
    0.52
    Activations Density 0.049%

    No Known Activations