© 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. 7-GEMMASCOPE-2-RES-16K
    4. 13435
    Prev
    Next
    INDEX
    Explanations

    world war 2, nazi germany, napoleon

    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_7_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
    ğın
    1.07
    телю
    1.06
    й
    1.01
    ගත
    1.01
    йы
    0.99
     thugs
    0.97
    шку
    0.96
    uleux
    0.91
    йын
    0.91
    מ
    0.90
    POSITIVE LOGITS
     AAS
    1.21
    𝐣
    1.10
    nae
    1.09
    tained
    1.07
     Antrieb
    1.07
     ATR
    1.04
    ృద్ధి
    1.04
    TON
    1.03
    𝐤
    1.03
    NAM
    1.03
    Activations Density 0.010%

    No Known Activations