© 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-262K
    4. 143384
    Prev
    Next
    INDEX
    Explanations

    causal relationships and sequence

    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
    চ্ছুক
    0.45
     beatae
    0.44
    གྲ
    0.44
    UInteger
    0.43
     ост
    0.43
    Normalized
    0.42
    ꞎ
    0.42
    仨
    0.41
    etään
    0.41
    Seminar
    0.41
    POSITIVE LOGITS
     making
    0.50
    件
    0.50
     weapon
    0.46
     oro
    0.46
     app
    0.45
     bracelets
    0.43
     servings
    0.43
     sourcing
    0.42
     acquisition
    0.42
     acquiring
    0.42
    Activations Density 0.010%

    No Known Activations