© 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. 84381
    Prev
    Next
    INDEX
    Explanations

    comparing different concepts

    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
    त्स
    0.46
     principalmente
    0.44
    بسم
    0.43
    Chand
    0.43
    ts
    0.42
     organize
    0.42
    ྩ
    0.41
    始め
    0.41
    ᑯ
    0.41
    rxjs
    0.41
    POSITIVE LOGITS
     λεπ
    0.47
    ędzy
    0.47
     shearing
    0.46
     գ
    0.45
    ifika
    0.45
    wór
    0.45
    ą
    0.45
     dreamy
    0.44
    akyat
    0.44
     주는
    0.43
    Activations Density 0.009%

    No Known Activations