© 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. 104241
    Prev
    Next
    INDEX
    Explanations

    all that apply

    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
     seis
    0.60
     six
    0.58
     cinco
    0.57
     sexto
    0.56
     recién
    0.54
     sustancias
    0.54
     etiquetas
    0.54
    뵌
    0.54
     pill
    0.52
    征
    0.52
    POSITIVE LOGITS
    to
    0.85
    that
    0.70
    not
    0.57
    them
    0.57
    ts
    0.57
    they
    0.57
    ý
    0.57
    the
    0.56
     উদ্য
    0.55
    their
    0.55
    Activations Density 0.001%

    No Known Activations