© 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. 112852
    Prev
    Next
    INDEX
    Explanations

    words before certain nouns

    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
     જોડ
    0.52
    飏
    0.50
     живело
    0.50
    ukiy
    0.47
     ಇದಕ್ಕೆ
    0.47
    ević
    0.47
     باہنی
    0.47
     સૌથી
    0.47
     samma
    0.46
     Aynı
    0.46
    POSITIVE LOGITS
    0.58
     ber
    0.52
     record
    0.50
     O
    0.47
    '
    0.46
    .
    0.46
     brainstorming
    0.45
     questions
    0.45
     h
    0.44
     tab
    0.44
    Activations Density 0.002%

    No Known Activations