© 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-3-1B
    3. 13-GEMMASCOPE-2-RES-16K
    4. 8784
    Prev
    Next
    INDEX
    Explanations

    account status warnings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_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
    <start_of_image>
    1.35
    วา
    1.14
    นี
    1.08
     คะ
    1.01
    มัน
    1.00
    นะ
    0.98
     เอง
    0.97
     มัน
    0.95
    芩
    0.94
    podob
    0.94
    POSITIVE LOGITS
     expansive
    1.76
     kaleidoscopic
    1.68
     multimillion
    1.64
     château
    1.59
     conservative
    1.58
     creș
    1.58
     culminating
    1.57
     tə
    1.56
     soundtracks
    1.55
     northwestern
    1.53
    Activations Density 0.054%

    No Known Activations