© 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
    3. 31-GEMMASCOPE-2-RES-16K
    4. 15369
    Prev
    Next
    INDEX
    Explanations

    legal terms or clauses

    np_acts-logits-general · gemini-2.5-flash-lite

    evaluating opportunities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    まずは
    0.46
    ご
    0.46
     VIP
    0.44
    活動
    0.43
    原
    0.43
    られ
    0.43
    VIP
    0.43
    沾
    0.43
     Pistons
    0.42
    托
    0.42
    POSITIVE LOGITS
    Song
    0.48
    lsen
    0.47
    answers
    0.46
    blonde
    0.46
    song
    0.46
     وطالبات
    0.45
    Violence
    0.45
     Song
    0.45
     Analyses
    0.44
     errorMessage
    0.44
    Activations Density 0.000%

    No Known Activations