© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 7831
    Prev
    Next
    INDEX
    Explanations

    twin girls, layers, best quality, Square

    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
    gur
    1.09
    ture
    0.99
    tra
    0.98
    tan
    0.95
    了
    0.92
    tod
    0.91
    да
    0.91
    oric
    0.91
    t
    0.90
    tat
    0.89
    POSITIVE LOGITS
     télévision
    1.21
     hyperactivity
    1.18
    メートル
    1.14
    人数
    1.14
     Antwerp
    1.12
     connecter
    1.11
     desayuno
    1.11
    happiness
    1.10
     décoration
    1.10
     pence
    1.10
    Activations Density 0.000%

    No Known Activations