© 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. 14906
    Prev
    Next
    INDEX
    Explanations

    passive voice, Crusades, conditional

    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
    zení
    2.52
     alır
    2.47
    پلز
    2.43
     ćel
    2.38
    yilda
    2.37
    ष्मान
    2.35
    nitř
    2.32
    س
    2.30
    ření
    2.29
    libat
    2.28
    POSITIVE LOGITS
     promise
    2.15
     straining
    2.09
     yielding
    2.06
     course
    2.05
    stock
    1.99
     abandonment
    1.97
    ingo
    1.97
    abandon
    1.96
     allied
    1.96
     departing
    1.95
    Activations Density 0.002%

    No Known Activations