© 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. 29049
    Prev
    Next
    INDEX
    Explanations

    purpose or introducing context

    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
     retriever
    0.50
     confound
    0.46
    "
    0.45
     means
    0.45
     whereby
    0.43
     policy
    0.42
    াল
    0.41
     savings
    0.41
     champion
    0.41
     lineWidth
    0.40
    POSITIVE LOGITS
    rabbitmq
    0.44
    پ
    0.41
     ایکسپریس
    0.41
    ipasi
    0.40
     Monitors
    0.40
    də
    0.40
    mongodb
    0.39
     যাবত
    0.39
    йович
    0.39
    Founded
    0.38
    Activations Density 0.000%

    No Known Activations