© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 8690
    Prev
    Next
    INDEX
    Explanations

    model: identifying AI identity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_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
    s
    0.65
     ح
    0.63
     Gods
    0.61
     Plugins
    0.60
     pokemon
    0.59
     moteurs
    0.58
    cnn
    0.58
     Hass
    0.57
     java
    0.57
     Pokémon
    0.57
    POSITIVE LOGITS
    يفة
    0.96
    絕
    0.96
    મને
    0.96
     기준으로
    0.91
     그리고
    0.91
    두
    0.90
     Kandid
    0.90
    >≥</
    0.89
     등장
    0.89
    그리고
    0.89
    Activations Density 23.190%

    No Known Activations