© 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. 7-GEMMASCOPE-2-RES-16K
    7. 1910
    Prev
    Next
    INDEX
    Explanations

    programming library calls

    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
     দেওয়া
    2.63
     দেওয়ার
    2.59
    лни
    2.49
    ফল
    2.44
     lungo
    2.38
    uleux
    2.35
     courte
    2.34
    ❘
    2.34
    -----+
    2.30
     couvert
    2.30
    POSITIVE LOGITS
    <bos>
    3.35
    s
    3.01
    tw
    2.63
    tų
    2.59
    si
    2.52
     ​​
    2.40
     đoàn
    2.37
     गर्लफ्रेंड
    2.35
     Процитовано
    2.31
    磡
    2.30
    Activations Density 0.450%

    No Known Activations